NeurIPS 2020 Papers

Offline reinforcement learning (RL), also known as batch RL, offers the prospect of policy optimization from large pre-recorded datasets without online environment interaction. It addresses challenges with regard to the cost of data collection and safety, both of which are particularly pertinent to real-world applications of RL. Unfortunately, most off-policy algorithms perform poorly when learning from a fixed dataset. In this paper, we propose a novel offline RL algorithm to learn policies from data using a form of critic-regularized regression (CRR). We find that CRR performs surprisingly well and scales to tasks with high-dimensional state and action spaces -- outperforming several state-of-the-art offline RL algorithms by a significant margin on a wide range of benchmark tasks.

One-shot weight sharing methods have recently drawn great attention in neural architecture search due to high efficiency and competitive performance. However, weight sharing across models has an inherent deficiency, i.e., insufficient training of subnetworks in the hypernetwork. To alleviate this problem, we present a simple yet effective architecture distillation method. The central idea is that subnetworks can learn collaboratively and teach each other throughout the training process, aiming to boost the convergence of individual models. We introduce the concept of prioritized path, which refers to the architecture candidates exhibiting superior performance during training. Distilling knowledge from the prioritized paths is able to boost the training of subnetworks. Since the prioritized paths are changed on the fly depending on their performance and complexity, the final obtained paths are the cream of the crop. We directly select the most promising one from the prioritized paths as the final architecture, without using other complex search methods, such as reinforcement learning or evolution algorithms. The experiments on ImageNet verify such path distillation method can improve the convergence ratio and performance of the hypernetwork, as well as boosting the training of subnetworks. The discovered architectures achieve superior performance compared to the recent MobileNetV3 and EfficientNet families under aligned settings. Moreover, the experiments on object detection and more challenging search space show the generality and robustness of the proposed method. Code and models are available at \url{https://github.com/neurips-20/cream.git}.

Invertible neural networks based on coupling flows (CF-INNs) have various machine learning applications such as image synthesis and representation learning. However, their desirable characteristics such as analytic invertibility come at the cost of restricting the functional forms. This poses a question on their representation power: are CF-INNs universal approximators for invertible functions? Without a universality, there could be a well-behaved invertible transformation that the CF-INN can never approximate, hence it would render the model class unreliable. We answer this question by showing a convenient criterion: a CF-INN is universal if its layers contain affine coupling and invertible linear functions as special cases. As its corollary, we can affirmatively resolve a previously unsolved problem: whether normalizing flow models based on affine coupling can be universal distributional approximators. In the course of proving the universality, we prove a general theorem to show the equivalence of the universality for certain diffeomorphism classes, a theoretical insight that is of interest by itself.

The task of vision-and-language navigation (VLN) requires an agent to follow text instructions to find its way through simulated household environments. A prominent challenge is to train an agent capable of generalising to new environments at test time, rather than one that simply memorises trajectories and visual details observed during training. We propose a new learning strategy that learns both from observations and generated counterfactual environments. We describe an effective algorithm to generate counterfactual observations on the fly for VLN, as linear combinations of existing environments. Simultaneously, we encourage the agent's actions to remain stable between original and counterfactual environments through our novel training objective-effectively removing the spurious features that otherwise bias the agent. Our experiments show that this technique provides significant improvements in generalisation on benchmarks for Room-to-Room navigation and Embodied Question Answering.

Algorithms are commonly used to predict outcomes under a particular decision or intervention, such as predicting likelihood of default if a loan is approved. Generally, to learn such counterfactual prediction models from observational data on historical decisions and corresponding outcomes, one must measure all factors that jointly affect the outcome and the decision taken. Motivated by decision support applications, we study the counterfactual prediction task in the setting where all relevant factors are captured in the historical data, but it is infeasible, undesirable, or impermissible to use some such factors in the prediction model. We refer to this setting as runtime confounding. We propose a doubly-robust procedure for learning counterfactual prediction models in this setting. Our theoretical analysis and experimental results suggest that our method often outperforms competing approaches. We also present a validation procedure for evaluating the performance of counterfactual prediction methods.

Estimating counterfactual outcome of different treatments from observational data is an important problem to assist decision making in a variety of fields. Among the various forms of treatment specification, bundle treatment has been widely adopted in many scenarios, such as recommendation systems and online marketing. The bundle treatment usually can be abstracted as a high dimensional binary vector, which makes it more challenging for researchers to remove the confounding bias in observational data. In this work, we assume the existence of low dimensional latent structure underlying bundle treatment. Via the learned latent representations of treatments, we propose a novel variational sample re-weighting (VSR) method to eliminate confounding bias by decorrelating the treatments and confounders. Finally, we conduct extensive experiments to demonstrate that the predictive model trained on this re-weighted dataset can achieve more accurate counterfactual outcome prediction.

Many dynamic processes, including common scenarios in robotic control and reinforcement learning (RL), involve a set of interacting subprocesses. Though the subprocesses are not independent, their interactions are often sparse, and the dynamics at any given time step can often be decomposed into locally independent} causal mechanisms. Such local causal structures can be leveraged to improve the sample efficiency of sequence prediction and off-policy reinforcement learning. We formalize this by introducing local causal models (LCMs), which are induced from a global causal model by conditioning on a subset of the state space. We propose an approach to inferring these structures given an object-oriented state representation, as well as a novel algorithm for Counterfactual Data Augmentation (CoDA). CoDA uses local structures and an experience replay to generate counterfactual experiences that are causally valid in the global model. We find that CoDA significantly improves the performance of RL agents in locally factored tasks, including the batch-constrained and goal-conditioned settings. Code available at https://github.com/spitis/mrl.

Weakly-supervised vision-language grounding aims to localize a target moment in a video or a specific region in an image according to the given sentence query, where only video-level or image-level sentence annotations are provided during training. Most existing approaches employ the MIL-based or reconstruction-based paradigms for the WSVLG task, but the former heavily depends on the quality of randomly-selected negative samples and the latter cannot directly optimize the visual-textual alignment score. In this paper, we propose a novel Counterfactual Contrastive Learning (CCL) to develop sufficient contrastive training between counterfactual positive and negative results, which are based on robust and destructive counterfactual transformations. Concretely, we design three counterfactual transformation strategies from the feature-, interaction- and relation-level, where the feature-level method damages the visual features of selected proposals, interaction-level approach confuses the vision-language interaction and relation-level strategy destroys the context clues in proposal relationships. Extensive experiments on five vision-language grounding datasets verify the effectiveness of our CCL paradigm.

The widespread adoption of deep learning is often attributed to its automatic feature construction with minimal inductive bias. However, in many real-world tasks, the learned function is intended to satisfy domain-specific constraints. We focus on monotonicity constraints, which are common and require that the function's output increases with increasing values of specific input features. We develop a counterexample-guided technique to provably enforce monotonicity constraints at prediction time. Additionally, we propose a technique to use monotonicity as an inductive bias for deep learning. It works by iteratively incorporating monotonicity counterexamples in the learning process. Contrary to prior work in monotonic learning, we target general ReLU neural networks and do not further restrict the hypothesis space. We have implemented these techniques in a tool called COMET. Experiments on real-world datasets demonstrate that our approach achieves state-of-the-art results compared to existing monotonic learners, and can improve the model quality compared to those that were trained without taking monotonicity constraints into account.

In this paper, we propose a fully differentiable pipeline for estimating accurate dense correspondences between 3D point clouds. The proposed pipeline is an extension and a generalization of the functional maps framework. However, instead of using the Laplace-Beltrami eigenfunctions as done in virtually all previous works in this domain, we demonstrate that learning the basis from data can both improve robustness and lead to better accuracy in challenging settings. We interpret the basis as a learned embedding into a higher dimensional space. Following the functional map paradigm the optimal transformation in this embedding space must be linear and we propose a separate architecture aimed at estimating the transformation by learning optimal descriptor functions. This leads to the first end-to-end trainable functional map-based correspondence approach in which both the basis and the descriptors are learned from data. Interestingly, we also observe that learning a canonical embedding leads to worse results, suggesting that leaving an extra linear degree of freedom to the embedding network gives it more robustness, thereby also shedding light onto the success of previous methods. Finally, we demonstrate that our approach achieves state-of-the-art results in challenging non-rigid 3D point cloud correspondence applications.

We propose a distributionally robust model for the influence maximization problem. Unlike the classical independent cascade model of Kempe et al (2003), this model's diffusion process is adversarially adapted to the choice of seed set. So instead of optimizing under the assumption that all influence relationships in the network are independent, we seek a seed set whose expected influence under the worst correlation, i.e., the ``worst-case, expected influence", is maximized. We show that this worst-case influence can be efficiently computed, and though the optimization is NP-hard, a (1 - 1/e) approximation guarantee holds. We also analyze the structure to the adversary's choice of diffusion process, and contrast with established models. Beyond the key computational advantages, we also study the degree to which the independence assumption may be considered costly, and provide insights from numerical experiments comparing the adversarial and independent cascade model.

Coresets are small data summaries that are sufficient for model training. They can be maintained online, enabling efficient handling of large data streams under resource constraints. However, existing constructions are limited to simple models such as k-means and logistic regression. In this work, we propose a novel coreset construction via cardinality-constrained bilevel optimization. We show how our framework can efficiently generate coresets for deep neural networks, and demonstrate its empirical benefits in continual learning and in streaming settings.

Modern neural networks have the capacity to overfit noisy labels frequently found in real-world datasets. Although great progress has been made, existing techniques are very limited in providing theoretical guarantees for the performance of the neural networks trained with noisy labels. To tackle this challenge, we propose a novel approach with strong theoretical guarantees for robust training of neural networks trained with noisy labels. The key idea behind our method is to select subsets of clean data points that provide an approximately low-rank Jacobian matrix. We then prove that gradient descent applied to the subsets cannot overfit the noisy labels, without regularization or early stopping. Our extensive experiments corroborate our theory and demonstrate that deep networks trained on our subsets achieve a significantly superior performance, e.g., 7% increase in accuracy on mini Webvision with 50% noisy labels, compared to state-of-the art.

A panel dataset contains features or observations for multiple individuals over multiple time periods and regression problems with panel data are common in statistics and applied ML. When dealing with massive datasets, coresets have emerged as a valuable tool from a computational, storage and privacy perspective, as one needs to work with and share much smaller datasets. However, results on coresets for regression problems thus far have only been available for cross-sectional data ($N$ individuals each observed for a single time unit) or longitudinal data (a single individual observed for $T>1$ time units), but there are no results for panel data ($N>1$, $T>1$). This paper introduces the problem of coresets to panel data settings; we first define coresets for several variants of regression problems with panel data and then present efficient algorithms to construct coresets of size that are independent of $N$ and $T$, and only polynomially depend on $1/\varepsilon$ (where $\varepsilon$ is the error parameter) and the number of regression parameters. Our approach is based on the Feldman-Langberg framework in which a key step is to upper bound the “total sensitivity” that is roughly the sum of maximum influences of all individual-time pairs taken over all possible choices of regression parameters. Empirically, we assess our approach with a synthetic and a real-world datasets; the coreset sizes constructed using our approach are much smaller than the full dataset and coresets indeed accelerate the running time of computing the regression objective.

Coreset is usually a small weighted subset of $n$ input points in $\mathbb{R}^d$, that provably approximates their loss function for a given set of queries (models, classifiers, etc.). Coresets become increasingly common in machine learning since existing heuristics or inefficient algorithms may be improved by running them possibly many times on the small coreset that can be maintained for streaming distributed data. Coresets can be obtained by sensitivity (importance) sampling, where its size is proportional to the total sum of sensitivities. Unfortunately, computing the sensitivity of each point is problem dependent and may be harder to compute than the original optimization problem at hand. We suggest a generic framework for computing sensitivities (and thus coresets) for wide family of loss functions which we call near-convex functions. This is by suggesting the $f$-SVD factorization that generalizes the SVD factorization of matrices to functions. Example applications include coresets that are either new or significantly improves previous results, such as SVM, Logistic regression, M-estimators, and $\ell_z$-regression. Experimental results and open source are also provided.

Consider a team of cooperative players that take actions in a networked-environment. At each turn, each player chooses an action and receives a reward that is an unknown function of all the players' actions. The goal of the team of players is to learn to play together the action profile that maximizes the sum of their rewards. However, players cannot observe the actions or rewards of other players, and can only get this information by communicating with their neighbors. We design a distributed learning algorithm that overcomes the informational bias players have towards maximizing the rewards of nearby players they got more information about. We assume twice continuously differentiable reward functions and constrained convex and compact action sets. Our communication graph is a random time-varying graph that follows an ergodic Markov chain. We prove that even if at every turn players take actions based only on the small random subset of the players' rewards that they know, our algorithm converges with probability 1 to the set of stationary points of (projected) gradient ascent on the sum of rewards function. Hence, if the sum of rewards is concave, then the algorithm converges with probability 1 to the optimal action profile.

Numerous deep reinforcement learning agents have been proposed, and each of them has its strengths and flaws. In this work, we present a Cooperative Heterogeneous Deep Reinforcement Learning (CHDRL) framework that can learn a policy by integrating the advantages of heterogeneous agents. Specifically, we propose a cooperative learning framework that classifies heterogeneous agents into two classes: global agents and local agents. Global agents are off-policy agents that can utilize experiences from the other agents. Local agents are either on-policy agents or population-based evolutionary algorithms (EAs) agents that can explore the local area effectively. We employ global agents, which are sample-efficient, to guide the learning of local agents so that local agents can benefit from the sample-efficient agents and simultaneously maintain their advantages, e.g., stability. Global agents also benefit from effective local searches. Experimental studies on a range of continuous control tasks from the Mujoco benchmark show that CHDRL achieves better performance compared with state-of-the-art baselines.

Learning from spatio-temporal data has numerous applications such as human-behavior analysis, object tracking, video compression, and physics simulation. However, existing methods still perform poorly on challenging video tasks such as long-term forecasting. This is because these kinds of challenging tasks require learning long-term spatio-temporal correlations in the video sequence. In this paper, we propose a higher-order convolutional LSTM model that can efficiently learn these correlations, along with a succinct representations of the history. This is accomplished through a novel tensor train module that performs prediction by combining convolutional features across time. To make this feasible in terms of computation and memory requirements, we propose a novel convolutional tensor-train decomposition of the higher-order model. This decomposition reduces the model complexity by jointly approximating a sequence of convolutional kernels as a low-rank tensor-train factorization. As a result, our model outperforms existing approaches, but uses only a fraction of parameters, including the baseline models. Our results achieve state-of-the-art performance in a wide range of applications and datasets, including the multi-steps video prediction on the Moving-MNIST-2 and KTH action datasets as well as early activity recognition on the Something-Something V2 dataset.

While recent generative models for 2D images achieve impressive visual results, they clearly lack the ability to perform 3D reasoning. This heavily restricts the degree of control over generated objects as well as the possible applications of such models. In this work, we bridge this gap by leveraging recent advances in differentiable rendering. We design a framework that can generate triangle meshes and associated high-resolution texture maps, using only 2D supervision from single-view natural images. A key contribution of our work is the encoding of the mesh and texture as 2D representations, which are semantically aligned and can be easily modeled by a 2D convolutional GAN. We demonstrate the efficacy of our method on Pascal3D+ Cars and CUB, both in an unconditional setting and in settings where the model is conditioned on class labels, attributes, and text. Finally, we propose an evaluation methodology that assesses the mesh and texture quality separately.