Jin, Chi


Provable Meta-Learning of Linear Representations

arXiv.org Artificial Intelligence

Meta-learning, or learning-to-learn, seeks to design algorithms that can utilize previous experience to rapidly learn new skills or adapt to new environments. Representation learning---a key tool for performing meta-learning---learns a data representation that can transfer knowledge across multiple tasks, which is essential in regimes where data is scarce. Despite a recent surge of interest in the practice of meta-learning, the theoretical underpinnings of meta-learning algorithms are lacking, especially in the context of learning transferable representations. In this paper, we focus on the problem of multi-task linear regression---in which multiple linear regression models share a common, low-dimensional linear representation. Here, we provide provably fast, sample-efficient algorithms to address the dual challenges of (1) learning a common set of features from multiple, related tasks, and (2) transferring this knowledge to new, unseen tasks. Both are central to the general problem of meta-learning. Finally, we complement these results by providing information-theoretic lower bounds on the sample complexity of learning these linear features, showing that our algorithms are optimal up to logarithmic factors.


Provable Self-Play Algorithms for Competitive Reinforcement Learning

arXiv.org Artificial Intelligence

This paper studies competitive reinforcement learning (competitive RL), that is, reinforcement learning with two or more agents taking actions simultaneously, but each maximizing their own reward. Competitive RL is a major branch of the more general setting of multi-agent reinforcement learning (MARL), with the specification that the agents have conflicting rewards (so that they essentially compete with each other) yet can be trained in a centralized fashion (i.e. each agent has access to the other agents' policies) (Crandall and Goodrich, 2005). There are substantial recent progresses in competitive RL, in particular in solving hard multi-player games such as GO (Silver et al., 2017), Starcraft (Vinyals et al., 2019), and Dota 2 (OpenAI, 2018). A key highlight in their approaches is the successful use of self-play for achieving superhuman performance in absence of human knowledge or expert opponents. These self-play algorithms are able to learn a good policy for all players from scratch through repeatedly playing the current policies against each other and performing policy updates using these self-played game trajectories. The empirical success of self-play has challenged the conventional wisdom that expert opponents are necessary for achieving good performance, and calls for a better theoretical understanding. In this paper, we take initial steps towards understanding the effectiveness of self-play algorithms in competitive RL from a theoretical perspective.


Dimensionality Dependent PAC-Bayes Margin Bound

Neural Information Processing Systems

Margin is one of the most important concepts in machine learning. Previous margin bounds, both for SVM and for boosting, are dimensionality independent. A major advantage of this dimensionality independency is that it can explain the excellent performance of SVM whose feature spaces are often of high or infinite dimension. In this paper we address the problem whether such dimensionality independency is intrinsic for the margin bounds. We prove a dimensionality dependent PAC-Bayes margin bound.


Provable Efficient Online Matrix Completion via Non-convex Stochastic Gradient Descent

Neural Information Processing Systems

Matrix completion, where we wish to recover a low rank matrix by observing a few entries from it, is a widely studied problem in both theory and practice with wide applications. Most of the provable algorithms so far on this problem have been restricted to the offline setting where they provide an estimate of the unknown matrix using all observations simultaneously. However, in many applications, the online version, where we observe one entry at a time and dynamically update our estimate, is more appealing. While existing algorithms are efficient for the offline setting, they could be highly inefficient for the online setting. In this paper, we propose the first provable, efficient online algorithm for matrix completion.


On the Local Minima of the Empirical Risk

Neural Information Processing Systems

Population risk is always of primary interest in machine learning; however, learning algorithms only have access to the empirical risk. Even for applications with nonconvex non-smooth losses (such as modern deep networks), the population risk is generally significantly more well behaved from an optimization point of view than the empirical risk. In particular, sampling can create many spurious local minima. We consider a general framework which aims to optimize a smooth nonconvex function $F$ (population risk) given only access to an approximation $f$ (empirical risk) that is pointwise close to $F$ (i.e., $ orm{F-f}_{\infty} \le u$). Our objective is to find the $\epsilon$-approximate local minima of the underlying function $F$ while avoiding the shallow local minima---arising because of the tolerance $ u$---which exist only in $f$.


Is Q-Learning Provably Efficient?

Neural Information Processing Systems

Model-free reinforcement learning (RL) algorithms directly parameterize and update value functions or policies, bypassing the modeling of the environment. They are typically simpler, more flexible to use, and thus more prevalent in modern deep RL than model-based approaches. However, empirical work has suggested that they require large numbers of samples to learn. The theoretical question of whether not model-free algorithms are in fact \emph{sample efficient} is one of the most fundamental questions in RL. The problem is unsolved even in the basic scenario with finitely many states and actions.


Local Maxima in the Likelihood of Gaussian Mixture Models: Structural Results and Algorithmic Consequences

Neural Information Processing Systems

We provide two fundamental results on the population (infinite-sample) likelihood function of Gaussian mixture models with $M \geq 3$ components. Our first main result shows that the population likelihood function has bad local maxima even in the special case of equally-weighted mixtures of well-separated and spherical Gaussians. We prove that the log-likelihood value of these bad local maxima can be arbitrarily worse than that of any global optimum, thereby resolving an open question of Srebro (2007). Our second main result shows that the EM algorithm (or a first-order variant of it) with random initialization will converge to bad critical points with probability at least $1-e {-\Omega(M)}$. We further establish that a first-order variant of EM will not converge to strict saddle points almost surely, indicating that the poor performance of the first-order method can be attributed to the existence of bad local maxima rather than bad saddle points.


Stochastic Cubic Regularization for Fast Nonconvex Optimization

Neural Information Processing Systems

This paper proposes a stochastic variant of a classic algorithm---the cubic-regularized Newton method [Nesterov and Polyak]. The proposed algorithm efficiently escapes saddle points and finds approximate local minima for general smooth, nonconvex functions in only $\mathcal{\tilde{O}}(\epsilon {-3.5})$ stochastic gradient and stochastic Hessian-vector product evaluations. The latter can be computed as efficiently as stochastic gradients. This improves upon the $\mathcal{\tilde{O}}(\epsilon {-4})$ rate of stochastic gradient descent. Our rate matches the best-known result for finding local minima without requiring any delicate acceleration or variance-reduction techniques.


Gradient Descent Can Take Exponential Time to Escape Saddle Points

Neural Information Processing Systems

Although gradient descent (GD) almost always escapes saddle points asymptotically [Lee et al., 2016], this paper shows that even with fairly natural random initialization schemes and non-pathological functions, GD can be significantly slowed down by saddle points, taking exponential time to escape. On the other hand, gradient descent with perturbations [Ge et al., 2015, Jin et al., 2017] is not slowed down by saddle points--it can find an approximate local minimizer in polynomial time. This result implies that GD is inherently slower than perturbed GD, and justifies the importance of adding perturbations for efficient non-convex optimization. While our focus is theoretical, we also present experiments that illustrate our theoretical findings. Papers published at the Neural Information Processing Systems Conference.


Reward-Free Exploration for Reinforcement Learning

arXiv.org Machine Learning

Exploration is widely regarded as one of the most challenging aspects of reinforcement learning (RL), with many naive approaches succumbing to exponential sample complexity. To isolate the challenges of exploration, we propose a new "reward-free RL" framework. In the exploration phase, the agent first collects trajectories from an MDP $\mathcal{M}$ without a pre-specified reward function. After exploration, it is tasked with computing near-optimal policies under for $\mathcal{M}$ for a collection of given reward functions. This framework is particularly suitable when there are many reward functions of interest, or when the reward function is shaped by an external agent to elicit desired behavior. We give an efficient algorithm that conducts $\tilde{\mathcal{O}}(S^2A\mathrm{poly}(H)/\epsilon^2)$ episodes of exploration and returns $\epsilon$-suboptimal policies for an arbitrary number of reward functions. We achieve this by finding exploratory policies that visit each "significant" state with probability proportional to its maximum visitation probability under any possible policy. Moreover, our planning procedure can be instantiated by any black-box approximate planner, such as value iteration or natural policy gradient. We also give a nearly-matching $\Omega(S^2AH^2/\epsilon^2)$ lower bound, demonstrating the near-optimality of our algorithm in this setting.