arXiv subjects

Simon S. Du

Publications and source records attributed to Simon S. Du.

At least 91 records · Page 5Linked to original sources

arXiv2021

Bilinear Classes: A Structural Framework for Provable Generalization in RL

This work introduces Bilinear Classes, a new structural framework, which permit generalization in reinforcement learning in a wide variety of settings through the use of function approximation. The framework incorporates nearly all existing models in which a polynomial sample complexity is achievable, and, notably, also includes new models, such as the Linear $Q^*/V^*$ model in which both the optimal $Q$-function and the optimal $V$-function are linear in some known feature space. Our main result provides an RL algorithm which has polynomial sample complexity for Bilinear Classes; notably, this sample complexity is stated in terms of a reduction to the generalization error of an underlying supervised learning sub-problem. These bounds nearly match the best known sample complexity bounds for existing models. Furthermore, this framework also extends to the infinite dimensional (RKHS) setting: for the the Linear $Q^*/V^*$ model, linear MDPs, and linear mixture MDPs, we provide sample complexities that have no explicit dependence on the explicit feature dimension (which could be infinite), but instead depends only on information theoretic quantities.

cs.LG↗

arXiv2021

When is Particle Filtering Efficient for Planning in Partially Observed Linear Dynamical Systems?

Particle filtering is a popular method for inferring latent states in stochastic dynamical systems, whose theoretical properties have been well studied in machine learning and statistics communities. In many control problems, e.g., partially observed linear dynamical systems (POLDS), oftentimes the inferred latent state is further used for planning at each step. This paper initiates a rigorous study on the efficiency of particle filtering for sequential planning, and gives the first particle complexity bounds. Though errors in past actions may affect the future, we are able to bound the number of particles needed so that the long-run reward of the policy based on particle filtering is close to that based on exact inference. In particular, we show that, in stable systems, polynomially many particles suffice. Key in our proof is a coupling of the ideal sequence based on the exact planning and the sequence generated by approximate planning based on particle filtering. We believe this technique can be useful in other sequential decision-making problems.

cs.LG↗

arXiv2021

Fine-Grained Gap-Dependent Bounds for Tabular MDPs via Adaptive Multi-Step Bootstrap

This paper presents a new model-free algorithm for episodic finite-horizon Markov Decision Processes (MDP), Adaptive Multi-step Bootstrap (AMB), which enjoys a stronger gap-dependent regret bound. The first innovation is to estimate the optimal $Q$-function by combining an optimistic bootstrap with an adaptive multi-step Monte Carlo rollout. The second innovation is to select the action with the largest confidence interval length among admissible actions that are not dominated by any other actions. We show when each state has a unique optimal action, AMB achieves a gap-dependent regret bound that only scales with the sum of the inverse of the sub-optimality gaps. In contrast, Simchowitz and Jamieson (2019) showed all upper-confidence-bound (UCB) algorithms suffer an additional $Ω\left(\frac{S}{Δ_{min}}\right)$ regret due to over-exploration where $Δ_{min}$ is the minimum sub-optimality gap and $S$ is the number of states. We further show that for general MDPs, AMB suffers an additional $\frac{|Z_{mul}|}{Δ_{min}}$ regret, where $Z_{mul}$ is the set of state-action pairs $(s,a)$'s satisfying $a$ is a non-unique optimal action for $s$. We complement our upper bound with a lower bound showing the dependency on $\frac{|Z_{mul}|}{Δ_{min}}$ is unavoidable for any consistent algorithm. This lower bound also implies a separation between reinforcement learning and contextual bandits.

cs.LG↗

arXiv2021

Gap-Dependent Bounds for Two-Player Markov Games

As one of the most popular methods in the field of reinforcement learning, Q-learning has received increasing attention. Recently, there have been more theoretical works on the regret bound of algorithms that belong to the Q-learning class in different settings. In this paper, we analyze the cumulative regret when conducting Nash Q-learning algorithm on 2-player turn-based stochastic Markov games (2-TBSG), and propose the very first gap dependent logarithmic upper bounds in the episodic tabular setting. This bound matches the theoretical lower bound only up to a logarithmic term. Furthermore, we extend the conclusion to the discounted game setting with infinite horizon and propose a similar gap dependent logarithmic regret bound. Also, under the linear MDP assumption, we obtain another logarithmic regret for 2-TBSG, in both centralized and independent settings.

cs.LG↗

arXiv2021

Is Reinforcement Learning More Difficult Than Bandits? A Near-optimal Algorithm Escaping the Curse of Horizon

Episodic reinforcement learning and contextual bandits are two widely studied sequential decision-making problems. Episodic reinforcement learning generalizes contextual bandits and is often perceived to be more difficult due to long planning horizon and unknown state-dependent transitions. The current paper shows that the long planning horizon and the unknown state-dependent transitions (at most) pose little additional difficulty on sample complexity. We consider the episodic reinforcement learning with $S$ states, $A$ actions, planning horizon $H$, total reward bounded by $1$, and the agent plays for $K$ episodes. We propose a new algorithm, \textbf{M}onotonic \textbf{V}alue \textbf{P}ropagation (MVP), which relies on a new Bernstein-type bonus. Compared to existing bonus constructions, the new bonus is tighter since it is based on a well-designed monotonic value function. In particular, the \emph{constants} in the bonus should be subtly setting to ensure optimism and monotonicity. We show MVP enjoys an $O\left(\left(\sqrt{SAK} + S^2A\right) \poly\log \left(SAHK\right)\right)$ regret, approaching the $Ω\left(\sqrt{SAK}\right)$ lower bound of \emph{contextual bandits} up to logarithmic terms. Notably, this result 1) \emph{exponentially} improves the state-of-the-art polynomial-time algorithms by Dann et al. [2019] and Zanette et al. [2019] in terms of the dependency on $H$, and 2) \emph{exponentially} improves the running time in [Wang et al. 2020] and significantly improves the dependency on $S$, $A$ and $K$ in sample complexity.

cs.LG↗

arXiv2021

Global Convergence of Gradient Descent for Asymmetric Low-Rank Matrix Factorization

We study the asymmetric low-rank factorization problem: \[\min_{\mathbf{U} \in \mathbb{R}^{m \times d}, \mathbf{V} \in \mathbb{R}^{n \times d}} \frac{1}{2}\|\mathbf{U}\mathbf{V}^\top -\mathbfΣ\|_F^2\] where $\mathbfΣ$ is a given matrix of size $m \times n$ and rank $d$. This is a canonical problem that admits two difficulties in optimization: 1) non-convexity and 2) non-smoothness (due to unbalancedness of $\mathbf{U}$ and $\mathbf{V}$). This is also a prototype for more complex problems such as asymmetric matrix sensing and matrix completion. Despite being non-convex and non-smooth, it has been observed empirically that the randomly initialized gradient descent algorithm can solve this problem in polynomial time. Existing theories to explain this phenomenon all require artificial modifications of the algorithm, such as adding noise in each iteration and adding a balancing regularizer to balance the $\mathbf{U}$ and $\mathbf{V}$. This paper presents the first proof that shows randomly initialized gradient descent converges to a global minimum of the asymmetric low-rank factorization problem with a polynomial rate. For the proof, we develop 1) a new symmetrization technique to capture the magnitudes of the symmetry and asymmetry, and 2) a quantitative perturbation analysis to approximate matrix derivatives. We believe both are useful for other related non-convex problems.

math.OC↗

arXiv2021

Corruption Robust Active Learning

We conduct theoretical studies on streaming-based active learning for binary classification under unknown adversarial label corruptions. In this setting, every time before the learner observes a sample, the adversary decides whether to corrupt the label or not. First, we show that, in a benign corruption setting (which includes the misspecification setting as a special case), with a slight enlargement on the hypothesis elimination threshold, the classical RobustCAL framework can (surprisingly) achieve nearly the same label complexity guarantee as in the non-corrupted setting. However, this algorithm can fail in the general corruption setting. To resolve this drawback, we propose a new algorithm which is provably correct without any assumptions on the presence of corruptions. Furthermore, this algorithm enjoys the minimax label complexity in the non-corrupted setting (which is achieved by RobustCAL) and only requires $\tilde{\mathcal{O}}(C_{\mathrm{total}})$ additional labels in the corrupted setting to achieve $\mathcal{O}(\varepsilon + \frac{C_{\mathrm{total}}}{n})$, where $\varepsilon$ is the target accuracy, $C_{\mathrm{total}}$ is the total number of corruptions and $n$ is the total number of unlabeled samples.

cs.LG↗

arXiv2021

On the Power of Multitask Representation Learning in Linear MDP

While multitask representation learning has become a popular approach in reinforcement learning (RL), theoretical understanding of why and when it works remains limited. This paper presents analyses for the statistical benefit of multitask representation learning in linear Markov Decision Process (MDP) under a generative model. In this paper, we consider an agent to learn a representation function $ϕ$ out of a function class $Φ$ from $T$ source tasks with $N$ data per task, and then use the learned $\hatϕ$ to reduce the required number of sample for a new task. We first discover a \emph{Least-Activated-Feature-Abundance} (LAFA) criterion, denoted as $κ$, with which we prove that a straightforward least-square algorithm learns a policy which is $\tilde{O}(H^2\sqrt{\frac{\mathcal{C}(Φ)^2 κd}{NT}+\frac{κd}{n}})$ sub-optimal. Here $H$ is the planning horizon, $\mathcal{C}(Φ)$ is $Φ$'s complexity measure, $d$ is the dimension of the representation (usually $d\ll \mathcal{C}(Φ)$) and $n$ is the number of samples for the new task. Thus the required $n$ is $O(κd H^4)$ for the sub-optimality to be close to zero, which is much smaller than $O(\mathcal{C}(Φ)^2κd H^4)$ in the setting without multitask representation learning, whose sub-optimality gap is $\tilde{O}(H^2\sqrt{\frac{κ\mathcal{C}(Φ)^2d}{n}})$. This theoretically explains the power of multitask representation learning in reducing sample complexity. Further, we note that to ensure high sample efficiency, the LAFA criterion $κ$ should be small. In fact, $κ$ varies widely in magnitude depending on the different sampling distribution for new task. This indicates adaptive sampling technique is important to make $κ$ solely depend on $d$. Finally, we provide empirical results of a noisy grid-world environment to corroborate our theoretical findings.

cs.LG↗

arXiv2021

Provable Adaptation across Multiway Domains via Representation Learning

This paper studies zero-shot domain adaptation where each domain is indexed on a multi-dimensional array, and we only have data from a small subset of domains. Our goal is to produce predictors that perform well on \emph{unseen} domains. We propose a model which consists of a domain-invariant latent representation layer and a domain-specific linear prediction layer with a low-rank tensor structure. Theoretically, we present explicit sample complexity bounds to characterize the prediction error on unseen domains in terms of the number of domains with training data and the number of data per domain. To our knowledge, this is the first finite-sample guarantee for zero-shot domain adaptation. In addition, we provide experiments on two-way MNIST and four-way fiber sensing datasets to demonstrate the effectiveness of our proposed model.

cs.LG↗

arXiv2021

Impact of Representation Learning in Linear Bandits

We study how representation learning can improve the efficiency of bandit problems. We study the setting where we play $T$ linear bandits with dimension $d$ concurrently, and these $T$ bandit tasks share a common $k (\ll d)$ dimensional linear representation. For the finite-action setting, we present a new algorithm which achieves $\widetilde{O}(T\sqrt{kN} + \sqrt{dkNT})$ regret, where $N$ is the number of rounds we play for each bandit. When $T$ is sufficiently large, our algorithm significantly outperforms the naive algorithm (playing $T$ bandits independently) that achieves $\widetilde{O}(T\sqrt{d N})$ regret. We also provide an $Ω(T\sqrt{kN} + \sqrt{dkNT})$ regret lower bound, showing that our algorithm is minimax-optimal up to poly-logarithmic factors. Furthermore, we extend our algorithm to the infinite-action setting and obtain a corresponding regret bound which demonstrates the benefit of representation learning in certain regimes. We also present experiments on synthetic and real-world data to illustrate our theoretical findings and demonstrate the effectiveness of our proposed algorithms.

cs.LG↗

arXiv2021

Few-Shot Learning via Learning the Representation, Provably

This paper studies few-shot learning via representation learning, where one uses $T$ source tasks with $n_1$ data per task to learn a representation in order to reduce the sample complexity of a target task for which there is only $n_2 (\ll n_1)$ data. Specifically, we focus on the setting where there exists a good \emph{common representation} between source and target, and our goal is to understand how much of a sample size reduction is possible. First, we study the setting where this common representation is low-dimensional and provide a fast rate of $O\left(\frac{\mathcal{C}\left(Φ\right)}{n_1T} + \frac{k}{n_2}\right)$; here, $Φ$ is the representation function class, $\mathcal{C}\left(Φ\right)$ is its complexity measure, and $k$ is the dimension of the representation. When specialized to linear representation functions, this rate becomes $O\left(\frac{dk}{n_1T} + \frac{k}{n_2}\right)$ where $d (\gg k)$ is the ambient input dimension, which is a substantial improvement over the rate without using representation learning, i.e. over the rate of $O\left(\frac{d}{n_2}\right)$. This result bypasses the $Ω(\frac{1}{T})$ barrier under the i.i.d. task assumption, and can capture the desired property that all $n_1T$ samples from source tasks can be \emph{pooled} together for representation learning. Next, we consider the setting where the common representation may be high-dimensional but is capacity-constrained (say in norm); here, we again demonstrate the advantage of representation learning in both high-dimensional linear regression and neural network learning. Our results demonstrate representation learning can fully utilize all $n_1T$ samples from source tasks.

cs.LG↗

arXiv2021

Improved Corruption Robust Algorithms for Episodic Reinforcement Learning

We study episodic reinforcement learning under unknown adversarial corruptions in both the rewards and the transition probabilities of the underlying system. We propose new algorithms which, compared to the existing results in (Lykouris et al., 2020), achieve strictly better regret bounds in terms of total corruptions for the tabular setting. To be specific, firstly, our regret bounds depend on more precise numerical values of total rewards corruptions and transition corruptions, instead of only on the total number of corrupted episodes. Secondly, our regret bounds are the first of their kind in the reinforcement learning setting to have the number of corruptions show up additively with respect to $\min\{\sqrt{T}, \text{PolicyGapComplexity}\}$ rather than multiplicatively. Our results follow from a general algorithmic framework that combines corruption-robust policy elimination meta-algorithms, and plug-in reward-free exploration sub-algorithms. Replacing the meta-algorithm or sub-algorithm may extend the framework to address other corrupted settings with potentially more structure.

cs.LG↗

arXiv2021

How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks

We study how neural networks trained by gradient descent extrapolate, i.e., what they learn outside the support of the training distribution. Previous works report mixed empirical results when extrapolating with neural networks: while feedforward neural networks, a.k.a. multilayer perceptrons (MLPs), do not extrapolate well in certain simple tasks, Graph Neural Networks (GNNs) -- structured networks with MLP modules -- have shown some success in more complex tasks. Working towards a theoretical explanation, we identify conditions under which MLPs and GNNs extrapolate well. First, we quantify the observation that ReLU MLPs quickly converge to linear functions along any direction from the origin, which implies that ReLU MLPs do not extrapolate most nonlinear functions. But, they can provably learn a linear target function when the training distribution is sufficiently "diverse". Second, in connection to analyzing the successes and limitations of GNNs, these results suggest a hypothesis for which we provide theoretical and empirical evidence: the success of GNNs in extrapolating algorithmic tasks to new data (e.g., larger graphs or edge weights) relies on encoding task-specific non-linearities in the architecture or features. Our theoretical analysis builds on a connection of over-parameterized networks to the neural tangent kernel. Empirically, our theory holds across different training settings.

cs.LG↗

arXiv2021

$Q$-learning with Logarithmic Regret

This paper presents the first non-asymptotic result showing that a model-free algorithm can achieve a logarithmic cumulative regret for episodic tabular reinforcement learning if there exists a strictly positive sub-optimality gap in the optimal $Q$-function. We prove that the optimistic $Q$-learning studied in [Jin et al. 2018] enjoys a ${\mathcal{O}}\left(\frac{SA\cdot \mathrm{poly}\left(H\right)}{Δ_{\min}}\log\left(SAT\right)\right)$ cumulative regret bound, where $S$ is the number of states, $A$ is the number of actions, $H$ is the planning horizon, $T$ is the total number of steps, and $Δ_{\min}$ is the minimum sub-optimality gap. This bound matches the information theoretical lower bound in terms of $S,A,T$ up to a $\log\left(SA\right)$ factor. We further extend our analysis to the discounted setting and obtain a similar logarithmic cumulative regret bound.

cs.LG↗

arXiv2021

A Provably Efficient Algorithm for Linear Markov Decision Process with Low Switching Cost

Many real-world applications, such as those in medical domains, recommendation systems, etc, can be formulated as large state space reinforcement learning problems with only a small budget of the number of policy changes, i.e., low switching cost. This paper focuses on the linear Markov Decision Process (MDP) recently studied in [Yang et al 2019, Jin et al 2020] where the linear function approximation is used for generalization on the large state space. We present the first algorithm for linear MDP with a low switching cost. Our algorithm achieves an $\widetilde{O}\left(\sqrt{d^3H^4K}\right)$ regret bound with a near-optimal $O\left(d H\log K\right)$ global switching cost where $d$ is the feature dimension, $H$ is the planning horizon and $K$ is the number of episodes the agent plays. Our regret bound matches the best existing polynomial algorithm by [Jin et al 2020] and our switching cost is exponentially smaller than theirs. When specialized to tabular MDP, our switching cost bound improves those in [Bai et al 2019, Zhang et al 20020]. We complement our positive result with an $Ω\left(dH/\log d\right)$ global switching cost lower bound for any no-regret algorithm.

cs.LG↗

arXiv2020

Provably Efficient Exploration for Reinforcement Learning Using Unsupervised Learning

Motivated by the prevailing paradigm of using unsupervised learning for efficient exploration in reinforcement learning (RL) problems [tang2017exploration,bellemare2016unifying], we investigate when this paradigm is provably efficient. We study episodic Markov decision processes with rich observations generated from a small number of latent states. We present a general algorithmic framework that is built upon two components: an unsupervised learning algorithm and a no-regret tabular RL algorithm. Theoretically, we prove that as long as the unsupervised learning algorithm enjoys a polynomial sample complexity guarantee, we can find a near-optimal policy with sample complexity polynomial in the number of latent states, which is significantly smaller than the number of observations. Empirically, we instantiate our framework on a class of hard exploration problems to demonstrate the practicality of our theory.

cs.LG↗

arXiv2020

Nearly Minimax Optimal Reward-free Reinforcement Learning

We study the reward-free reinforcement learning framework, which is particularly suitable for batch reinforcement learning and scenarios where one needs policies for multiple reward functions. This framework has two phases. In the exploration phase, the agent collects trajectories by interacting with the environment without using any reward signal. In the planning phase, the agent needs to return a near-optimal policy for arbitrary reward functions. We give a new efficient algorithm, \textbf{S}taged \textbf{S}ampling + \textbf{T}runcated \textbf{P}lanning (\algoname), which interacts with the environment at most $O\left( \frac{S^2A}{ε^2}\text{poly}\log\left(\frac{SAH}ε\right) \right)$ episodes in the exploration phase, and guarantees to output a near-optimal policy for arbitrary reward functions in the planning phase. Here, $S$ is the size of state space, $A$ is the size of action space, $H$ is the planning horizon, and $ε$ is the target accuracy relative to the total reward. Notably, our sample complexity scales only \emph{logarithmically} with $H$, in contrast to all existing results which scale \emph{polynomially} with $H$. Furthermore, this bound matches the minimax lower bound $Ω\left(\frac{S^2A}{ε^2}\right)$ up to logarithmic factors. Our results rely on three new techniques : 1) A new sufficient condition for the dataset to plan for an $ε$-suboptimal policy; 2) A new way to plan efficiently under the proposed condition using soft-truncated planning; 3) Constructing extended MDP to maximize the truncated accumulative rewards efficiently.

cs.LG↗

arXiv2020

Near-Linear Time Local Polynomial Nonparametric Estimation with Box Kernels

Local polynomial regression (Fan and Gijbels 1996) is an important class of methods for nonparametric density estimation and regression problems. However, straightforward implementation of local polynomial regression has quadratic time complexity which hinders its applicability in large-scale data analysis. In this paper, we significantly accelerate the computation of local polynomial estimates by novel applications of multi-dimensional binary indexed trees (Fenwick 1994). Both time and space complexity of our proposed algorithm is nearly linear in the number of input data points. Simulation results confirm the efficiency and effectiveness of our proposed approach.

stat.CO↗