Search Results for author:
Found 11 papers, 1 papers with code
Online Convex Optimization in the Random Order Model
Focusing on two important families of online tasks, one which generalizes online linear and logistic regression, and the other being online PCA, we show that under standard well-conditioned-data assumptions (that are often being made in the corresponding offline settings), standard online gradient descent (OGD) methods become much more efficient in the random-order model.
Solving Non-Rectangular Reward-Robust MDPs via Frequency Regularization
In robust Markov decision processes (RMDPs), it is assumed that the reward and the transition dynamics lie in a given uncertainty set.
Bring Your Own (Non-Robust) Algorithm to Solve Robust MDPs by Estimating The Worst Kernel
Robust Markov Decision Processes (RMDPs) provide a framework for sequential decision-making that is robust to perturbations on the transition kernel.
Policy Gradient for Rectangular Robust Markov Decision Processes
We provide a closed-form expression for the worst occupation measure.
An Efficient Solution to s-Rectangular Robust Markov Decision Processes
We present an efficient robust value iteration for \texttt{s}-rectangular robust Markov Decision Processes (MDPs) with a time complexity comparable to standard (non-robust) MDPs which is significantly faster than any existing method.
Policy Gradient for Reinforcement Learning with General Utilities
The policy gradient theorem proves to be a cornerstone in Linear RL due to its elegance and ease of implementability.
Efficient Policy Iteration for Robust Markov Decision Processes via Regularization
But we don't have a clear understanding to exploit this equivalence, to do policy improvement steps to get the optimal value function or policy.
STORM+: Fully Adaptive SGD with Recursive Momentum for Nonconvex Optimization
In this work we propose $\rm{STORM}^{+}$, a new method that is completely parameter-free, does not require large batch-sizes, and obtains the optimal $O(1/T^{1/3})$ rate for finding an approximate stationary point.
Online to Offline Conversions, Universality and Adaptive Minibatch Sizes
We present an approach towards convex optimization that relies on a novel scheme which converts adaptive online algorithms into offline methods.
Fast Rates for Exp-concave Empirical Risk Minimization
In this setting, we establish the first evidence that ERM is able to attain fast generalization rates, and show that the expected loss of the ERM solution in $d$ dimensions converges to the optimal expected loss in a rate of $d/n$.
Bandit Convex Optimization: Towards Tight Bounds
Bandit Convex Optimization (BCO) is a fundamental framework for decision making under uncertainty, which generalizes many problems from the realm of online and statistical learning.
