ICLR.2023

| Total: 1584

#1 REVISITING PRUNING AT INITIALIZATION THROUGH THE LENS OF RAMANUJAN GRAPH [PDF72] [Copy] [Kimi218] [REL]

Authors: Duc Hoang, Shiwei Liu, Radu Marculescu, Zhangyang Wang

Pruning neural networks at initialization (PaI) has received an upsurge of interest due to its end-to-end saving potential. PaI is able to find sparse subnetworks at initialization that can achieve comparable performance to the full networks. These methods can surpass the trivial baseline of random pruning but suffer from a significant performance gap compared to post-training pruning. Previous approaches firmly rely on weights, gradients, and sanity checks as primary signals when conducting PaI analysis. To better understand the underlying mechanism of PaI, we propose to interpret it through the lens of the Ramanujan Graph - a class of expander graphs that are sparse while being highly connected. It is often believed there should be a strong correlation between the Ramanujan graph and PaI since both are about finding sparse and well-connected neural networks. However, the finer-grained link relating highly sparse and connected networks to their relative performance (i.e., ranking of difference sparse structures at the same specific global sparsity) is still missing. We observe that not only the Ramanujan property for sparse networks shows no significant relationship to PaI’s relative performance, but maximizing it can also lead to the formation of pseudo-random graphs with no structural meanings. We reveal the underlying cause to be Ramanujan Graph’s strong assumption on the upper bound of the largest nontrivial eigenvalue (µˆ) of layers belonging to highly sparse networks. We hence propose Iterative Mean Difference of Bound (IMDB) as a mean to relax the µˆ upper bound. Likewise, we also show there exists a lower bound for µˆ, which we call the Normalized Random Coefficient (NaRC), that gives us an accurate assessment for when sparse but highly connected structure degenerates into naive randomness. Finally, we systematically analyze the behavior of various PaI methods and demonstrate the utility of our proposed metrics in characterizing PaI performance. We show that subnetworks preserving better the IMDB property correlate higher in performance, while NaRC provides us with a possible mean to locate the region where highly connected, highly sparse, and non-trivial Ramanujan expanders exist. Our code is available at: https://github.com/VITA-Group/ramanujan-on-pai.


#2 Confidential-PROFITT: Confidential PROof of FaIr Training of Trees [PDF16] [Copy] [Kimi64] [REL]

Authors: Ali Shahin Shamsabadi, Sierra Wyllie, Nicholas Franzese, Natalie Dullerud, Sébastien Gambs, Nicolas Papernot, Xiao Wang, Adrian Weller

Post hoc auditing of model fairness suffers from potential drawbacks: (1) auditing may be highly sensitive to the test samples chosen; (2) the model and/or its training data may need to be shared with an auditor thereby breaking confidentiality. We address these issues by instead providing a certificate that demonstrates that the learning algorithm itself is fair, and hence, as a consequence, so too is the trained model. We introduce a method to provide a confidential proof of fairness for training, in the context of widely used decision trees, which we term Confidential-PROFITT. We propose novel fair decision tree learning algorithms along with customized zero-knowledge proof protocols to obtain a proof of fairness that can be audited by a third party. Using zero-knowledge proofs enables us to guarantee confidentiality of both the model and its training data. We show empirically that bounding the information gain of each node with respect to the sensitive attributes reduces the unfairness of the final tree. In extensive experiments on the COMPAS, Communities and Crime, Default Credit, and Adult datasets, we demonstrate that a company can use Confidential-PROFITT to certify the fairness of their decision tree to an auditor in less than 2 minutes, thus indicating the applicability of our approach. This is true for both the demographic parity and equalized odds definitions of fairness. Finally, we extend Confidential-PROFITT to apply to ensembles of trees.


#3 Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics [PDF11] [Copy] [Kimi41] [REL]

Authors: Kuo-Hao Zeng, Luca Weihs, Roozbeh Mottaghi, Ali Farhadi

A common assumption when training embodied agents is that the impact of taking an action is stable; for instance, executing the ``move ahead'' action will always move the agent forward by a fixed distance, perhaps with some small amount of actuator-induced noise. This assumption is limiting; an agent may encounter settings that dramatically alter the impact of actions: a move ahead action on a wet floor may send the agent twice as far as it expects and using the same action with a broken wheel might transform the expected translation into a rotation. Instead of relying that the impact of an action stably reflects its pre-defined semantic meaning, we propose to model the impact of actions on-the-fly using latent embeddings. By combining these latent action embeddings with a novel, transformer-based, policy head, we design an Action Adaptive Policy (AAP). We evaluate our AAP on two challenging visual navigation tasks in the AI2-THOR and Habitat environments and show that our AAP is highly performant even when faced, at inference-time, with missing actions and, previously unseen, perturbed action spaces. Moreover, we observe significant improvement in robustness against these actions when evaluating in real-world scenarios.


#4 Rethinking the Expressive Power of GNNs via Graph Biconnectivity [PDF9] [Copy] [Kimi33] [REL]

Authors: Bohang Zhang, Shengjie Luo, Liwei Wang, Di He

Designing expressive Graph Neural Networks (GNNs) is a central topic in learning graph-structured data. While numerous approaches have been proposed to improve GNNs with respect to the Weisfeiler-Lehman (WL) test, for most of them, there is still a lack of deep understanding of what additional power they can systematically and provably gain. In this paper, we take a fundamentally different perspective to study the expressive power of GNNs beyond the WL test. Specifically, we introduce a novel class of expressivity metrics via graph biconnectivity and highlight their importance in both theory and practice. As biconnectivity can be easily calculated using simple algorithms that have linear computational costs, it is natural to expect that popular GNNs can learn it easily as well. However, after a thorough review of prior GNN architectures, we surprisingly find that most of them are not expressive for any of these metrics. The only exception is the ESAN framework (Bevilacqua et al., 2022), for which we give a theoretical justification of its power. We proceed to introduce a principled and more efficient approach, called the Generalized Distance Weisfeiler-Lehman (GD-WL), which is provably expressive for all biconnectivity metrics. Practically, we show GD-WL can be implemented by a Transformer-like architecture that preserves expressiveness and enjoys full parallelizability. A set of experiments on both synthetic and real datasets demonstrates that our approach can consistently outperform prior GNN architectures.


#5 3D generation on ImageNet [PDF7] [Copy] [Kimi32] [REL]

Authors: Ivan Skorokhodov, Aliaksandr Siarohin, Yinghao Xu, Jian Ren, Hsin-Ying Lee, Peter Wonka, Sergey Tulyakov

All existing 3D-from-2D generators are designed for well-curated single-category datasets, where all the objects have (approximately) the same scale, 3D location, and orientation, and the camera always points to the center of the scene. This makes them inapplicable to diverse, in-the-wild datasets of non-alignable scenes rendered from arbitrary camera poses. In this work, we develop a 3D generator with Generic Priors (3DGP): a 3D synthesis framework with more general assumptions about the training data, and show that it scales to very challenging datasets, like ImageNet. Our model is based on three new ideas. First, we incorporate an inaccurate off-the-shelf depth estimator into 3D GAN training via a special depth adaptation module to handle the imprecision. Then, we create a flexible camera model and a regularization strategy for it to learn its distribution parameters during training. Finally, we extend the recent ideas of transferring knowledge from pretrained classifiers into GANs for patch-wise trained models by employing a simple distillation-based technique on top of the discriminator. It achieves more stable training than the existing methods and speeds up the convergence by at least 40%. We explore our model on four datasets: SDIP Dogs $256^2$, SDIP Elephants $256^2$, LSUN Horses $256^2$, and ImageNet $256^2$ and demonstrate that 3DGP outperforms the recent state-of-the-art in terms of both texture and geometry quality. Code and visualizations: https://snap-research.github.io/3dgp.


#6 On the Sensitivity of Reward Inference to Misspecified Human Models [PDF4] [Copy] [Kimi21] [REL]

Authors: Joey Hong, Kush Bhatia, Anca Dragan

Inferring reward functions from human behavior is at the center of value alignment – aligning AI objectives with what we, humans, actually want. But doing so relies on models of how humans behave given their objectives. After decades of research in cognitive science, neuroscience, and behavioral economics, obtaining accurate human models remains an open research topic. This begs the question: how accurate do these models need to be in order for the reward inference to be accurate? On the one hand, if small errors in the model can lead to catastrophic error in inference, the entire framework of reward learning seems ill-fated, as we will never have perfect models of human behavior. On the other hand, if as our models improve, we can have a guarantee that reward accuracy also improves, this would show the benefit of more work on the modeling side. We study this question both theoretically and empirically. We do show that it is unfortunately possible to construct small adversarial biases in behavior that lead to arbitrarily large errors in the inferred reward. However, and arguably more importantly, we are also able to identify reasonable assumptions under which the reward inference error can be bounded linearly in the error in the human model. Finally, we verify our theoretical insights in discrete and continuous control tasks with simulated and human data.


#7 A Kernel Perspective of Skip Connections in Convolutional Networks [PDF15] [Copy] [Kimi29] [REL]

Authors: Daniel Barzilai, Amnon Geifman, Meirav Galun, Ronen Basri

Over-parameterized residual networks (ResNets) are amongst the most successful convolutional neural architectures for image processing. Here we study their properties through their Gaussian Process and Neural Tangent kernels. We derive explicit formulas for these kernels, analyze their spectra, and provide bounds on their implied condition numbers. Our results indicate that (1) with ReLU activation, the eigenvalues of these residual kernels decay polynomially at a similar rate compared to the same kernels when skip connections are not used, thus maintaining a similar frequency bias; (2) however, residual kernels are more locally biased. Our analysis further shows that the matrices obtained by these residual kernels yield favorable condition numbers at finite depths than those obtained without the skip connections, enabling therefore faster convergence of training with gradient descent.


#8 Aligning Model and Macaque Inferior Temporal Cortex Representations Improves Model-to-Human Behavioral Alignment and Adversarial Robustness [PDF2] [Copy] [Kimi21] [REL]

Authors: Joel Dapello, Kohitij Kar, Martin Schrimpf, Robert Geary, Michael Ferguson, David Cox, James DiCarlo

While some state-of-the-art artificial neural network systems in computer vision are strikingly accurate models of the corresponding primate visual processing, there are still many discrepancies between these models and the behavior of primates on object recognition tasks. Many current models suffer from extreme sensitivity to adversarial attacks and often do not align well with the image-by-image behavioral error patterns observed in humans. Previous research has provided strong evidence that primate object recognition behavior can be very accurately predicted by neural population activity in the inferior temporal (IT) cortex, a brain area in the late stages of the visual processing hierarchy. Therefore, here we directly test whether making the late stage representations of models more similar to that of macaque IT produces new models that exhibit more robust, primate-like behavior. We conducted chronic, large-scale multi-electrode recordings across the IT cortex in six non-human primates (rhesus macaques). We then use these data to fine-tune (end-to-end) the model "IT" representations such that they are more aligned with the biological IT representations, while preserving accuracy on object recognition tasks. We generate a cohort of models with a range of IT similarity scores validated on held-out animals across two image sets with distinct statistics. Across a battery of optimization conditions, we observed a strong correlation between the models' IT-likeness and alignment with human behavior, as well as an increase in its adversarial robustness. We further assessed the limitations of this approach and find that the improvements in behavioral alignment and adversarial robustness generalize across different image statistics, but not to object categories outside of those covered in our IT training set. Taken together, our results demonstrate that building models that are more aligned with the primate brain leads to more robust and human-like behavior, and call for larger neural data-sets to further augment these gains.


#9 Efficient Conditionally Invariant Representation Learning [PDF12] [Copy] [Kimi33] [REL]

Authors: Roman Pogodin, Namrata Deka, Yazhe Li, Danica Sutherland, Victor Veitch, Arthur Gretton

We introduce the Conditional Independence Regression CovariancE (CIRCE), a measure of conditional independence for multivariate continuous-valued variables. CIRCE applies as a regularizer in settings where we wish to learn neural features $\varphi(X)$ of data $X$ to estimate a target $Y$, while being conditionally independent of a distractor $Z$ given $Y$. Both $Z$ and $Y$ are assumed to be continuous-valued but relatively low dimensional, whereas $X$ and its features may be complex and high dimensional. Relevant settings include domain-invariant learning, fairness, and causal learning. The procedure requires just a single ridge regression from $Y$ to kernelized features of $Z$, which can be done in advance. It is then only necessary to enforce independence of $\varphi(X)$ from residuals of this regression, which is possible with attractive estimation properties and consistency guarantees. By contrast, earlier measures of conditional feature dependence require multiple regressions for each step of feature learning, resulting in more severe bias and variance, and greater computational cost. When sufficiently rich features are used, we establish that CIRCE is zero if and only if $\varphi(X) \perp \!\!\! \perp Z \mid Y$. In experiments, we show superior performance to previous methods on challenging benchmarks, including learning conditionally invariant image features. Code for image data experiments is available at github.com/namratadeka/circe.


#10 Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task [PDF8] [Copy] [Kimi17] [REL]

Authors: Kenneth Li, Aspen Hopkins, David Bau, Fernanda Viégas, Hanspeter Pfister, Martin Wattenberg

Language models show a surprising range of capabilities, but the source of their apparent competence is unclear. Do these networks just memorize a collection of surface statistics, or do they rely on internal representations of the process that generates the sequences they see? We investigate this question by applying a variant of the GPT model to the task of predicting legal moves in a simple board game, Othello. Although the network has no a priori knowledge of the game or its rules, we uncover evidence of an emergent nonlinear internal representation of the board state. Interventional experiments indicate this representation can be used to control the output of the network and create "latent saliency maps" that can help explain predictions in human terms.


#11 The Lie Derivative for Measuring Learned Equivariance [PDF5] [Copy] [Kimi11] [REL]

Authors: Nate Gruver, Marc A Finzi, Micah Goldblum, Andrew Wilson

Equivariance guarantees that a model's predictions capture key symmetries in data. When an image is translated or rotated, an equivariant model's representation of that image will translate or rotate accordingly. The success of convolutional neural networks has historically been tied to translation equivariance directly encoded in their architecture. The rising success of vision transformers, which have no explicit architectural bias towards equivariance, challenges this narrative and suggests that augmentations and training data might also play a significant role in their performance. In order to better understand the role of equivariance in recent vision models, we apply the Lie derivative, a method for measuring equivariance with strong mathematical foundations and minimal hyperparameters. Using the Lie derivative, we study the equivariance properties of hundreds of pretrained models, spanning CNNs, transformers, and Mixer architectures. The scale of our analysis allows us to separate the impact of architecture from other factors like model size or training method. Surprisingly, we find that many violations of equivariance can be linked to spatial aliasing in ubiquitous network layers, such as pointwise non-linearities, and that as models get larger and more accurate they tend to display more equivariance, regardless of architecture. For example, transformers can be more equivariant than convolutional neural networks after training.


#12 SimPer: Simple Self-Supervised Learning of Periodic Targets [PDF6] [Copy] [Kimi13] [REL]

Authors: Yuzhe Yang, Xin Liu, Jiang Wu, Silviu Borac, Dina Katabi, Ming-Zher Poh, Daniel McDuff

From human physiology to environmental evolution, important processes in nature often exhibit meaningful and strong periodic or quasi-periodic changes. Due to their inherent label scarcity, learning useful representations for periodic tasks with limited or no supervision is of great benefit. Yet, existing self-supervised learning (SSL) methods overlook the intrinsic periodicity in data, and fail to learn representations that capture periodic or frequency attributes. In this paper, we present SimPer, a simple contrastive SSL regime for learning periodic information in data. To exploit the periodic inductive bias, SimPer introduces customized augmentations, feature similarity measures, and a generalized contrastive loss for learning efficient and robust periodic representations. Extensive experiments on common real-world tasks in human behavior analysis, environmental sensing, and healthcare domains verify the superior performance of SimPer compared to state-of-the-art SSL methods, highlighting its intriguing properties including better data efficiency, robustness to spurious correlations, and generalization to distribution shifts.


#13 Modeling content creator incentives on algorithm-curated platforms [PDF2] [Copy] [Kimi5] [REL]

Authors: Jiri Hron, Karl Krauth, Michael Jordan, Niki Kilbertus, Sarah Dean

Content creators compete for user attention. Their reach crucially depends on algorithmic choices made by developers on online platforms. To maximize exposure, many creators adapt strategically, as evidenced by examples like the sprawling search engine optimization industry. This begets competition for the finite user attention pool. We formalize these dynamics in what we call an exposure game, a model of incentives induced by modern algorithms including factorization and (deep) two-tower architectures. We prove that seemingly innocuous algorithmic choices—e.g., non-negative vs. unconstrained factorization—significantly affect the existence and character of (Nash) equilibria in exposure games. We proffer use of creator behavior models like ours for an (ex-ante) pre-deployment audit. Such an audit can identify misalignment between desirable and incentivized content, and thus complement post-hoc measures like content filtering and moderation. To this end, we propose tools for numerically finding equilibria in exposure games, and illustrate results of an audit on the MovieLens and LastFM datasets. Among else, we find that the strategically produced content exhibits strong dependence between algorithmic exploration and content diversity, and between model expressivity and bias towards gender-based user and creator groups.


#14 DaxBench: Benchmarking Deformable Object Manipulation with Differentiable Physics [PDF2] [Copy] [Kimi4] [REL]

Authors: Siwei Chen, Yiqing Xu, Cunjun Yu, Linfeng Li, Xiao Ma, Zhongwen Xu, David Hsu

Deformable object manipulation (DOM) is a long-standing challenge in robotics and has attracted significant interest recently. This paper presents DaXBench, a differentiable simulation framework for DOM. While existing work often focuses on a specific type of deformable objects, DaXBench supports fluid, rope, cloth ...; it provides a general-purpose benchmark to evaluate widely different DOM methods, including planning, imitation learning, and reinforcement learning. DaXBench combines recent advances in deformable object simulation with JAX, a high-performance computational framework. All DOM tasks in DaXBench are wrapped with the OpenAI Gym API for easy integration with DOM algorithms. We hope that DaXBench provides to the research community a comprehensive, standardized benchmark and a valuable tool to support the development and evaluation of new DOM methods. The code and video are available online.


#15 Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation [PDF4] [Copy] [Kimi13] [REL]

Authors: Marius-Constantin Dinu, Markus Holzleitner, Maximilian Beck, Hoan Nguyen, Andrea Huber, Hamid Eghbalzadeh, Bernhard A. Moser, Sergei Pereverzyev, Sepp Hochreiter, Werner Zellinger

We study the problem of choosing algorithm hyper-parameters in unsupervised domain adaptation, i.e., with labeled data in a source domain and unlabeled data in a target domain, drawn from a different input distribution. We follow the strategy to compute several models using different hyper-parameters, and, to subsequently compute a linear aggregation of the models. While several heuristics exist that follow this strategy, methods are still missing that rely on thorough theories for bounding the target error. In this turn, we propose a method that extends weighted least squares to vector-valued functions, e.g., deep neural networks. We show that the target error of the proposed algorithm is asymptotically not worse than twice the error of the unknown optimal aggregation. We also perform a large scale empirical comparative study on several datasets, including text, images, electroencephalogram, body sensor signals and signals from mobile phones. Our method outperforms deep embedded validation (DEV) and importance weighted validation (IWV) on all datasets, setting a new state-of-the-art performance for solving parameter choice issues in unsupervised domain adaptation with theoretical error guarantees. We further study several competitive heuristics, all outperforming IWV and DEV on at least five datasets. However, our method outperforms each heuristic on at least five of seven datasets.


#16 Towards Stable Test-time Adaptation in Dynamic Wild World [PDF3] [Copy] [Kimi7] [REL]

Authors: Shuaicheng Niu, Jiaxiang Wu, Yifan Zhang, Zhiquan Wen, Yaofo Chen, Peilin Zhao, Mingkui Tan

Test-time adaptation (TTA) has shown to be effective at tackling distribution shifts between training and testing data by adapting a given model on test samples. However, the online model updating of TTA may be unstable and this is often a key obstacle preventing existing TTA methods from being deployed in the real world. Specifically, TTA may fail to improve or even harm the model performance when test data have: 1) mixed distribution shifts, 2) small batch sizes, and 3) online imbalanced label distribution shifts, which are quite common in practice. In this paper, we investigate the unstable reasons and find that the batch norm layer is a crucial factor hindering TTA stability. Conversely, TTA can perform more stably with batch-agnostic norm layers, i.e., group or layer norm. However, we observe that TTA with group and layer norms does not always succeed and still suffers many failure cases. By digging into the failure cases, we find that certain noisy test samples with large gradients may disturb the model adaption and result in collapsed trivial solutions, i.e., assigning the same class label for all samples. To address the above collapse issue, we propose a sharpness-aware and reliable entropy minimization method, called SAR, for further stabilizing TTA from two aspects: 1) remove partial noisy samples with large gradients, 2) encourage model weights to go to a flat minimum so that the model is robust to the remaining noisy samples. Promising results demonstrate that SAR performs more stably than prior methods and is computationally efficient under the above wild test scenarios.


#17 Near-optimal Policy Identification in Active Reinforcement Learning [PDF2] [Copy] [Kimi4] [REL]

Authors: Xiang Li, Viraj Mehta, Johannes Kirschner, Ian Char, Willie Neiswanger, Jeff Schneider, Andreas Krause, Ilija Bogunovic

Many real-world reinforcement learning tasks require control of complex dynamical systems that involve both costly data acquisition processes and large state spaces. In cases where the expensive transition dynamics can be readily evaluated at specified states (e.g., via a simulator), agents can operate in what is often referred to as planning with a \emph{generative model}. We propose the AE-LSVI algorithm for best policy identification, a novel variant of the kernelized least-squares value iteration (LSVI) algorithm that combines optimism with pessimism for active exploration (AE). AE-LSVI provably identifies a near-optimal policy \emph{uniformly} over an entire state space and achieves polynomial sample complexity guarantees that are independent of the number of states. When specialized to the recently introduced offline contextual Bayesian optimization setting, our algorithm achieves improved sample complexity bounds. Experimentally, we demonstrate that AE-LSVI outperforms other RL algorithms in a variety of environments when robustness to the initial state is required.


#18 Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve [PDF7] [Copy] [Kimi14] [REL]

Authors: Juhan Bae, Michael Zhang, Michael Ruan, Duanyang Wang, So Hasegawa, Jimmy Ba, Roger Grosse

Variational autoencoders (VAEs) are powerful tools for learning latent representations of data used in a wide range of applications. In practice, VAEs usually require multiple training rounds to choose the amount of information the latent variable should retain. This trade-off between the reconstruction error (distortion) and the KL divergence (rate) is typically parameterized by a hyperparameter $\beta$. In this paper, we introduce Multi-Rate VAE (MR-VAE), a computationally efficient framework for learning optimal parameters corresponding to various $\beta$ in a single training run. The key idea is to explicitly formulate a response function using hypernetworks that maps $\beta$ to the optimal parameters. MR-VAEs construct a compact response hypernetwork where the pre-activations are conditionally gated based on $\beta$. We justify the proposed architecture by analyzing linear VAEs and showing that it can represent response functions exactly for linear VAEs. With the learned hypernetwork, MR-VAEs can construct the rate-distortion curve without additional training and can be deployed with significantly less hyperparameter tuning. Empirically, our approach is competitive and often exceeds the performance of multiple $\beta$-VAEs training with minimal computation and memory overheads.


#19 In-context Reinforcement Learning with Algorithm Distillation [PDF5] [Copy] [Kimi12] [REL]

Authors: Michael Laskin, Luyu Wang, Junhyuk Oh, Emilio Parisotto, Stephen Spencer, Richie Steigerwald, DJ Strouse, Steven Hansen, Angelos Filos, Ethan Brooks, Maxime Gazeau, Himanshu Sahni, Satinder Singh, Volodymyr Mnih

We propose Algorithm Distillation (AD), a method for distilling reinforcement learning (RL) algorithms into neural networks by modeling their training histories with a causal sequence model. Algorithm Distillation treats learning to reinforcement learn as an across-episode sequential prediction problem. A dataset of learning histories is generated by a source RL algorithm, and then a causal transformer is trained by autoregressively predicting actions given their preceding learning histories as context. Unlike sequential policy prediction architectures that distill post-learning or expert sequences, AD is able to improve its policy entirely in-context without updating its network parameters. We demonstrate that AD can reinforcement learn in-context in a variety of environments with sparse rewards, combinatorial task structure, and pixel-based observations, and find that AD learns a more data-efficient RL algorithm than the one that generated the source data.


#20 SAM as an Optimal Relaxation of Bayes [PDF4] [Copy] [Kimi7] [REL]

Authors: Thomas Möllenhoff, Mohammad Emtiyaz Khan

Sharpness-aware minimization (SAM) and related adversarial deep-learning methods can drastically improve generalization, but their underlying mechanisms are not yet fully understood. Here, we establish SAM as a relaxation of the Bayes objective where the expected negative-loss is replaced by the optimal convex lower bound, obtained by using the so-called Fenchel biconjugate. The connection enables a new Adam-like extension of SAM to automatically obtain reasonable uncertainty estimates, while sometimes also improving its accuracy. By connecting adversarial and Bayesian methods, our work opens a new path to robustness.


#21 Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection [PDF5] [Copy] [Kimi9] [REL]

Authors: Jiajun Fan, Yuzheng Zhuang, Yuecheng Liu, Jianye HAO, Bin Wang, Jiangcheng Zhu, Hao Wang, Shu-Tao Xia

The exploration problem is one of the main challenges in deep reinforcement learning (RL). Recent promising works tried to handle the problem with population-based methods, which collect samples with diverse behaviors derived from a population of different exploratory policies. Adaptive policy selection has been adopted for behavior control. However, the behavior selection space is largely limited by the predefined policy population, which further limits behavior diversity. In this paper, we propose a general framework called Learnable Behavioral Control (LBC) to address the limitation, which a) enables a significantly enlarged behavior selection space via formulating a hybrid behavior mapping from all policies; b) constructs a unified learnable process for behavior selection. We introduce LBC into distributed off-policy actor-critic methods and achieve behavior control via optimizing the selection of the behavior mappings with bandit-based meta-controllers. Our agents have achieved 10077.52% mean human normalized score and surpassed 24 human world records within 1B training frames in the Arcade Learning Environment, which demonstrates our significant state-of-the-art (SOTA) performance without degrading the sample efficiency.


#22 Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Approach [PDF3] [Copy] [Kimi3] [REL]

Authors: Heshan Fernando, Han Shen, Miao Liu, Subhajit Chaudhury, Keerthiram Murugesan, Tianyi Chen

Many machine learning problems today have multiple objective functions. They appear either in learning with multiple criteria where learning has to make a trade-off between multiple performance metrics such as fairness, safety and accuracy; or, in multi-task learning where multiple tasks are optimized jointly, sharing inductive bias between them. This problems are often tackled by the multi-objective optimization framework. However, existing stochastic multi-objective gradient methods and its variants (e.g., MGDA, PCGrad, CAGrad, etc.) all adopt a biased noisy gradient direction, which leads to degraded empirical performance. To this end, we develop a stochastic multi-objective gradient correction (MoCo) method for multi-objective optimization. The unique feature of our method is that it can guarantee convergence without increasing the batch size even in the nonconvex setting. Simulations on multi-task supervised and reinforcement learning demonstrate the effectiveness of our method relative to the state-of-the-art methods.


#23 Encoding Recurrence into Transformers [PDF11] [Copy] [Kimi14] [REL]

Authors: Feiqing Huang, Kexin Lu, Yuxi Cai, Zhen Qin, Yanwen Fang, Guangjian Tian, Guodong Li

This paper novelly breaks down with ignorable loss an RNN layer into a sequence of simple RNNs, each of which can be further rewritten into a lightweight positional encoding matrix of a self-attention, named the Recurrence Encoding Matrix (REM). Thus, recurrent dynamics introduced by the RNN layer can be encapsulated into the positional encodings of a multihead self-attention, and this makes it possible to seamlessly incorporate these recurrent dynamics into a Transformer, leading to a new module, Self-Attention with Recurrence (RSA). The proposed module can leverage the recurrent inductive bias of REMs to achieve a better sample efficiency than its corresponding baseline Transformer, while the self-attention is used to model the remaining non-recurrent signals. The relative proportions of these two components are controlled by a data-driven gated mechanism, and the effectiveness of RSA modules are demonstrated by four sequential learning tasks.


#24 Sample-Efficient Reinforcement Learning by Breaking the Replay Ratio Barrier [PDF4] [Copy] [Kimi5] [REL]

Authors: Pierluca D'Oro, Max Schwarzer, Evgenii Nikishin, Pierre-Luc Bacon, Marc G Bellemare, Aaron Courville

Increasing the replay ratio, the number of updates of an agent's parameters per environment interaction, is an appealing strategy for improving the sample efficiency of deep reinforcement learning algorithms. In this work, we show that fully or partially resetting the parameters of deep reinforcement learning agents causes better replay ratio scaling capabilities to emerge. We push the limits of the sample efficiency of carefully-modified algorithms by training them using an order of magnitude more updates than usual, significantly improving their performance in the Atari 100k and DeepMind Control Suite benchmarks. We then provide an analysis of the design choices required for favorable replay ratio scaling to be possible and discuss inherent limits and tradeoffs.


#25 Compressing multidimensional weather and climate data into neural networks [PDF3] [Copy] [Kimi7] [REL]

Authors: Langwen Huang, Torsten Hoefler

Weather and climate simulations produce petabytes of high-resolution data that are later analyzed by researchers in order to understand climate change or severe weather. We propose a new method of compressing this multidimensional weather and climate data: a coordinate-based neural network is trained to overfit the data, and the resulting parameters are taken as a compact representation of the original grid-based data. While compression ratios range from 300x to more than 3,000x, our method outperforms the state-of-the-art compressor SZ3 in terms of weighted RMSE, MAE. It can faithfully preserve important large scale atmosphere structures and does not introduce significant artifacts.When using the resulting neural network as a 790x compressed dataloader to train the WeatherBench forecasting model, its RMSE increases by less than 2%. The three orders of magnitude compression democratizes access to high-resolution climate data and enables numerous new research directions.