A key challenge in applying reinforcement learning to safety-critical domains is understanding how to balance exploration (needed to attain good performance on the task) with safety (needed to avoid catastrophic failure). Although a growing line of work in reinforcement learning has investigated this area of "safe exploration," most existing techniques either 1) do not guarantee safety during the actual exploration process; and/or 2) limit the problem to a priori known and/or deterministic transition dynamics with strong smoothness assumptions. Addressing this gap, we propose Analogous Safe-state Exploration (ASE), an algorithm for provably safe exploration in MDPs with unknown, stochastic dynamics. Our method exploits analogies between state-action pairs to safely learn a near-optimal policy in a PAC-MDP sense. Additionally, ASE also guides exploration towards the most task-relevant states, which empirically results in significant improvements in terms of sample efficiency, when compared to existing methods.
The ability of overparameterized deep networks to generalize well has been linked to the fact that stochastic gradient descent (SGD) finds solutions that lie in flat, wide minima in the training loss -- minima where the output of the network is resilient to small random noise added to its parameters. So far this observation has been used to provide generalization guarantees only for neural networks whose parameters are either \textit{stochastic} or \textit{compressed}. In this work, we present a general PAC-Bayesian framework that leverages this observation to provide a bound on the original network learned -- a network that is deterministic and uncompressed. What enables us to do this is a key novelty in our approach: our framework allows us to show that if on training data, the interactions between the weight matrices satisfy certain conditions that imply a wide training loss minimum, these conditions themselves {\em generalize} to the interactions between the matrices on test data, thereby implying a wide test loss minimum. We then apply our general framework in a setup where we assume that the pre-activation values of the network are not too small (although we assume this only on the training data). In this setup, we provide a generalization guarantee for the original (deterministic, uncompressed) network, that does not scale with product of the spectral norms of the weight matrices -- a guarantee that would not have been possible with prior approaches.
We cast doubt on the power of uniform convergence-based generalization bounds to provide a complete picture of why overparameterized deep networks generalize well. While it is well-known that many existing bounds are numerically large, through a variety of experiments, we first bring to light another crucial and more concerning aspect of these bounds: in practice, these bounds can {\em increase} with the dataset size. Guided by our observations, we then present examples of overparameterized linear classifiers and neural networks trained by stochastic gradient descent (SGD) where uniform convergence provably cannot `explain generalization,' even if we take into account implicit regularization {\em to the fullest extent possible}. More precisely, even if we consider only the set of classifiers output by SGD that have test errors less than some small $\epsilon$, applying (two-sided) uniform convergence on this set of classifiers yields a generalization guarantee that is larger than $1-\epsilon$ and is therefore nearly vacuous.
Why does training deep neural networks using stochastic gradient descent (SGD) result in a generalization error that does not worsen with the number of parameters in the network? To answer this question, we advocate a notion of effective model capacity that is dependent on {\em a given random initialization of the network} and not just the training algorithm and the data distribution. We provide empirical evidences that demonstrate that the model capacity of SGD-trained deep networks is in fact restricted through implicit regularization of {\em the $\ell_2$ distance from the initialization}. We also provide theoretical arguments that further highlight the need for initialization-dependent notions of model capacity. We leave as open questions how and why distance from initialization is regularized, and whether it is sufficient to explain generalization.
Max-cut, clustering, and many other partitioning problems that are of significant importance to machine learning and other scientific fields are NP-hard, a reality that has motivated researchers to develop a wealth of approximation algorithms and heuristics. Although the best algorithm to use typically depends on the specific application domain, a worst-case analysis is often used to compare algorithms. This may be misleading if worst-case instances occur infrequently, and thus there is a demand for optimization methods which return the algorithm configuration best suited for the given application's typical inputs. We address this problem for clustering, max-cut, and other partitioning problems, such as integer quadratic programming, by designing computationally efficient and sample efficient learning algorithms which receive samples from an application-specific distribution over problem instances and learn a partitioning algorithm with high expected performance. Our algorithms learn over common integer quadratic programming and clustering algorithm families: SDP rounding algorithms and agglomerative clustering algorithms with dynamic programming. For our sample complexity analysis, we provide tight bounds on the pseudodimension of these algorithm classes, and show that surprisingly, even for classes of algorithms parameterized by a single parameter, the pseudo-dimension is superconstant. In this way, our work both contributes to the foundations of algorithm configuration and pushes the boundaries of learning theory, since the algorithm classes we analyze consist of multi-stage optimization procedures and are significantly more complex than classes typically studied in learning theory.
In this work we formally define the notions of adversarial perturbations, adversarial risk and adversarial training and analyze their properties. Our analysis provides several interesting insights into adversarial risk, adversarial training, and their relation to the classification risk, "traditional" training. We also show that adversarial training can result in models with better classification accuracy and can result in better explainable models than traditional training. Although adversarial training is computationally expensive, our results and insights suggest that one should prefer adversarial training over traditional risk minimization for learning complex models from data.
Despite the growing prominence of generative adversarial networks (GANs), optimization in GANs is still a poorly understood topic. In this paper, we analyze the "gradient descent" form of GAN optimization i.e., the natural setting where we simultaneously take small gradient steps in both generator and discriminator parameters. We show that even though GAN optimization does not correspond to a convex-concave game (even for simple parameterizations), under proper conditions, equilibrium points of this optimization procedure are still \emph{locally asymptotically stable} for the traditional GAN formulation. On the other hand, we show that the recently proposed Wasserstein GAN can have non-convergent limit cycles near equilibrium. Motivated by this stability analysis, we propose an additional regularization term for gradient descent GAN updates, which \emph{is} able to guarantee local stability for both the WGAN and the traditional GAN, and also shows practical promise in speeding up convergence and addressing mode collapse.
An important long-term goal in machine learning systems is to build learning agents that, like humans, can learn many tasks over their lifetime, and moreover use information from these tasks to improve their ability to do so efficiently. In this work, our goal is to provide new theoretical insights into the potential of this paradigm. In particular, we propose a lifelong learning framework that adheres to a novel notion of resource efficiency that is critical in many real-world domains where feature evaluations are costly. That is, our learner aims to reuse information from previously learned related tasks to learn future tasks in a feature-efficient manner. Furthermore, we consider novel combinatorial ways in which learning tasks can relate. Specifically, we design lifelong learning algorithms for two structurally different and widely used families of target functions: decision trees/lists and monomials/polynomials. We also provide strong feature-efficiency guarantees for these algorithms; in fact, we show that in order to learn future targets, we need only slightly more feature evaluations per training example than what is needed to predict on an arbitrary example using those targets. We also provide algorithms with guarantees in an agnostic model where not all the targets are related to each other. Finally, we also provide lower bounds on the performance of a lifelong learner in these models, which are in fact tight under some conditions.
Online decision tree learning algorithms typically examine all features of a new data point to update model parameters. We propose a novel alternative, Reinforcement Learning- based Decision Trees (RLDT), that uses Reinforcement Learning (RL) to actively examine a minimal number of features of a data point to classify it with high accuracy. Furthermore, RLDT optimizes a long term return, providing a better alternative to the traditional myopic greedy approach to growing decision trees. We demonstrate that this approach performs as well as batch learning algorithms and other online decision tree learning algorithms, while making significantly fewer queries about the features of the data points. We also show that RLDT can effectively handle concept drift.