Search Results for author:
Found 25 papers, 10 papers with code
Meta-learning the mirror map in policy mirror descent
Policy Mirror Descent (PMD) is a popular framework in reinforcement learning, serving as a unifying perspective that encompasses numerous algorithms.
Generalization Bounds for Label Noise Stochastic Gradient Descent
We develop generalization error bounds for stochastic gradient descent (SGD) with label noise in non-convex settings under uniform dissipativity and smoothness conditions.
Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity
An algorithm is sample-efficient if it uses a number of queries $n$ to the environment that is polynomial in the dimension $d$ of the problem.
A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence
Modern policy optimization methods in reinforcement learning, such as TRPO and PPO, owe their success to the use of parameterized policies.
Linear Convergence for Natural Policy Gradient with Log-linear Policy Parametrization
We analyze the convergence rate of the unregularized natural policy gradient algorithm with log-linear policy parametrizations in infinite-horizon discounted Markov decision processes.
Exponential Tail Local Rademacher Complexity Risk Bounds Without the Bernstein Condition
Our main result is an exponential-tail excess risk bound expressed in terms of the offset Rademacher complexity that yields results at least as sharp as those obtainable via the classical theory.
Time-independent Generalization Bounds for SGLD in Non-convex Settings
We establish generalization error bounds for stochastic gradient Langevin dynamics (SGLD) with constant learning rate under the assumptions of dissipativity and smoothness, a setting that has received increased attention in the sampling/optimization literature.
On Optimal Interpolation In Linear Regression
We identify a regime where the minimum-norm interpolator provably generalizes arbitrarily worse than the optimal response-linear achievable interpolator that we introduce, and validate with numerical experiments that the notion of optimality we consider can be achieved by interpolating methods that only use the training data as input in the case of an isotropic prior.
Dimension-Free Rates for Natural Policy Gradient in Multi-Agent Reinforcement Learning
Cooperative multi-agent reinforcement learning is a decentralized paradigm in sequential decision making where agents distributed over a network iteratively collaborate with neighbors to maximize global (network-wide) notions of rewards.
Comparing Classes of Estimators: When does Gradient Descent Beat Ridge Regression in Linear Models?
Methods for learning from data depend on various types of tuning parameters, such as penalization strength or step size.
Implicit Regularization in Matrix Sensing via Mirror Descent
We study discrete-time mirror descent applied to the unregularized empirical risk in matrix sensing.
Nearly Minimax-Optimal Rates for Noisy Sparse Phase Retrieval via Early-Stopped Mirror Descent
This paper studies early-stopped mirror descent applied to noisy sparse phase retrieval, which is the problem of recovering a $k$-sparse signal $\mathbf{x}^\star\in\mathbb{R}^n$ from a set of quadratic Gaussian measurements corrupted by sub-exponential noise.
A Continuous-Time Mirror Descent Approach to Sparse Phase Retrieval
We analyze continuous-time mirror descent applied to sparse phase retrieval, which is the problem of recovering sparse signals from a set of magnitude-only measurements.
Decentralised Learning with Random Features and Distributed Gradient Descent
Under standard source and capacity assumptions, we establish high probability bounds on the predictive performance for each agent as a function of the step size, number of iterations, inverse spectral gap of the communication matrix and number of Random Features.
Hadamard Wirtinger Flow for Sparse Phase Retrieval
We consider the problem of reconstructing an $n$-dimensional $k$-sparse signal from a set of noiseless magnitude-only measurements.
The Statistical Complexity of Early-Stopped Mirror Descent
Recently there has been a surge of interest in understanding implicit regularization properties of iterative gradient-based optimization algorithms.
Distributed Machine Learning with Sparse Heterogeneous Data
Motivated by distributed machine learning settings such as Federated Learning, we consider the problem of fitting a statistical model across a distributed collection of heterogeneous data sets whose similarity structure is encoded by a graph topology.
Implicit Regularization for Optimal Sparse Recovery
We investigate implicit regularization schemes for gradient descent methods applied to unpenalized least squares regression to solve the problem of reconstructing a sparse signal from an underdetermined system of linear measurements under the restricted isometry assumption.
Optimal Statistical Rates for Decentralised Non-Parametric Regression with Linear Speed-Up
We show that if agents hold sufficiently many samples with respect to the network size, then Distributed Gradient Descent achieves optimal statistical rates with a number of iterations that scales, up to a threshold, with the inverse of the spectral gap of the gossip matrix divided by the number of samples owned by each agent raised to a problem-dependent power.
Decentralized Cooperative Stochastic Bandits
We design a fully decentralized algorithm that uses an accelerated consensus procedure to compute (delayed) estimates of the average of rewards obtained by all the agents for each arm, and then uses an upper confidence bound (UCB) algorithm that accounts for the delay and error of the estimates.
Graph-Dependent Implicit Regularisation for Distributed Stochastic Subgradient Descent
We propose graph-dependent implicit regularisation strategies for distributed stochastic subgradient descent (Distributed SGD) for convex problems in multi-agent learning.
Accelerated consensus via Min-Sum Splitting
We apply the Min-Sum message-passing protocol to solve the consensus problem in distributed optimization.
A New Approach to Laplacian Solvers and Flow Problems
This paper investigates the behavior of the Min-Sum message passing scheme to solve systems of linear equations in the Laplacian matrices of graphs and to compute electric flows.
Scale-free network optimization: foundations and algorithms
We propose a notion of correlation in constrained optimization that is based on the sensitivity of the optimal solution upon perturbations of the constraints.
Fast Mixing for Discrete Point Processes
We show that if the set function (not necessarily submodular) displays a natural notion of decay of correlation, then, for $\beta$ small enough, it is possible to design fast mixing Markov chain Monte Carlo methods that yield error bounds on marginal approximations that do not depend on the size of the set $V$.
