Search Results for author:
Found 24 papers, 3 papers with code
Implicit Diffusion: Efficient Optimization through Stochastic Sampling
We present a new algorithm to optimize distributions defined implicitly by parameterized stochastic diffusions.
Contextual Bandits with Stage-wise Constraints
In the setting that the constraint is in expectation, we further specialize our results to multi-armed bandits and propose a computationally efficient algorithm for this setting with regret analysis.
Can a Transformer Represent a Kalman Filter?
We revisit the problem of Kalman Filtering in linear dynamical systems and show that Transformers can approximate the Kalman Filter in a strong sense.
Joint Representation Training in Sequential Tasks with Shared Structure
In contrast with previous work that have studied multi task RL in other function approximation models, we show that in the presence of bilinear optimization oracle and finite state action spaces there exists a computationally efficient algorithm for multitask MatrixRL via a reduction to quadratic programming.
Generalization Bounds for Data-Driven Numerical Linear Algebra
Our techniques are general, and provide generalization bounds for many other recently proposed data-driven algorithms in numerical linear algebra, covering both sketching-based and multigrid-based methods.
A Complete Characterization of Linear Estimators for Offline Policy Evaluation
Offline policy evaluation is a fundamental statistical problem in reinforcement learning that involves estimating the value function of some decision-making policy given data collected by a potentially different policy.
An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit
We study the problem of information sharing and cooperation in Multi-Player Multi-Armed bandits.
Parallelizing Contextual Bandits
Standard approaches to decision-making under uncertainty focus on sequential exploration of the space of decisions.
Towards a Dimension-Free Understanding of Adaptive Linear Control
We study the problem of adaptive control of the linear quadratic regulator for systems in very high, or even infinite dimension.
Near Optimal Policy Optimization via REPS
Since its introduction a decade ago, \emph{relative entropy policy search} (REPS) has demonstrated successful policy learning on a number of simulated and real-world robotic domains, not to mention providing algorithmic components used by many recently proposed reinforcement learning (RL) algorithms.
Regret Bound Balancing and Elimination for Model Selection in Bandits and RL
Finally, unlike recent efforts in model selection for linear stochastic bandits, our approach is versatile enough to also cover cases where the context information is generated by an adversarial environment, rather than a stochastic one.
Accelerated Message Passing for Entropy-Regularized MAP Inference
Maximum a posteriori (MAP) inference in discrete-valued Markov random fields is a fundamental problem in machine learning that involves identifying the most likely configuration of random variables given a distribution.
Stochastic Bandits with Linear Constraints
We propose an upper-confidence bound algorithm for this problem, called optimistic pessimistic linear bandit (OPLB), and prove an $\widetilde{\mathcal{O}}(\frac{d\sqrt{T}}{\tau-c_0})$ bound on its $T$-round regret, where the denominator is the difference between the constraint threshold and the cost of a known feasible action.
Dropout: Explicit Forms and Capacity Control
In deep learning, we show that the data-dependent regularizer due to dropout directly controls the Rademacher complexity of the underlying class of deep neural networks.
Is There an Analog of Nesterov Acceleration for MCMC?
We formulate gradient-based Markov chain Monte Carlo (MCMC) sampling as optimization on the space of probability measures, with Kullback-Leibler (KL) divergence as the objective functional.
Rademacher Complexity for Adversarially Robust Generalization
For binary linear classifiers, we prove tight bounds for the adversarial Rademacher complexity, and show that the adversarial Rademacher complexity is never smaller than its natural counterpart, and it has an unavoidable dimension dependence, unless the weight vector has bounded $\ell_1$ norm.
Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks
We provide polynomial bounds on the number of iterations for gradient descent to approximate the least squares matrix $\Phi$, in the case where the initial hypothesis $\Theta_1 = ... = \Theta_L = I$ has excess loss bounded by a small enough constant.
Defending Against Saddle Point Attack in Byzantine-Robust Distributed Learning
In this setting, the Byzantine machines may create fake local minima near a saddle point that is far away from any true local minimum, even when robust gradient estimators are used.
Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
In particular, these algorithms are shown to achieve order-optimal statistical error rates for strongly convex losses.
Spectrally-normalized margin bounds for neural networks
This paper presents a margin-based multiclass generalization bound for neural networks that scales with their margin-normalized "spectral complexity": their Lipschitz constant, meaning the product of the spectral norms of the weight matrices, times a certain correction factor.
Gradient Diversity: a Key Ingredient for Scalable Distributed Learning
It has been experimentally observed that distributed implementations of mini-batch stochastic gradient descent (SGD) algorithms exhibit speedup saturation and decaying generalization ability beyond a particular batch-size.
Convergence of Langevin MCMC in KL-divergence
Langevin diffusion is a commonly used tool for sampling from a given distribution.
Horizon-Independent Optimal Prediction with Log-Loss in Exponential Families
Keywords: SNML Exchangeability, Exponential Family, Online Learning, Logarithmic Loss, Bayesian Strategy, Jeffreys Prior, Fisher Information1
Advice-Efficient Prediction with Expert Advice
Advice-efficient prediction with expert advice (in analogy to label-efficient prediction) is a variant of prediction with expert advice game, where on each round of the game we are allowed to ask for advice of a limited number $M$ out of $N$ experts.
