Search Results for author:
Found 12 papers, 2 papers with code
Reusing Historical Trajectories in Natural Policy Gradient via Importance Sampling: Convergence and Convergence Rate
The efficient utilization of historical trajectories obtained from previous policies is essential for expediting policy optimization.
Approximate Bilevel Difference Convex Programming for Bayesian Risk Markov Decision Processes
We consider infinite-horizon Markov Decision Processes where parameters, such as transition probabilities, are unknown and estimated from data.
Risk-averse Contextual Multi-armed Bandit Problem with Linear Payoffs
In particular, we consider mean-variance as the risk criterion, and the best arm is the one with the largest mean-variance reward.
Robust Multi-Objective Bayesian Optimization Under Input Noise
In many manufacturing processes, the design parameters are subject to random input noise, resulting in a product that is often less performant than expected.
Noise Regularizes Over-parameterized Rank One Matrix Recovery, Provably
We investigate the role of noise in optimization algorithms for learning over-parameterized models.
Bayesian Risk Markov Decision Processes
We consider finite-horizon Markov Decision Processes where parameters, such as transition probabilities, are unknown and estimated from data.
Noisy Gradient Descent Converges to Flat Minima for Nonconvex Matrix Factorization
Numerous empirical evidences have corroborated the importance of noise in nonconvex optimization problems.
Bayesian Optimization of Risk Measures
We consider Bayesian optimization of objective functions of the form $\rho[ F(x, W) ]$, where $F$ is a black-box expensive-to-evaluate function and $\rho$ denotes either the VaR or CVaR risk measure, computed with respect to the randomness induced by the environmental random variable $W$.
Towards Understanding the Importance of Shortcut Connections in Residual Networks
We show, however, that gradient descent combined with proper normalization, avoids being trapped by the spurious local optimum, and converges to a global optimum in polynomial time, when the weight of the first layer is initialized at 0, and that of the second layer is initialized arbitrarily in a ball.
Towards Understanding the Importance of Noise in Training Neural Networks
Numerous empirical evidence has corroborated that the noise plays a crucial rule in effective and efficient training of neural networks.
Towards Understanding Acceleration Tradeoff between Momentum and Asynchrony in Nonconvex Stochastic Optimization
Asynchronous momentum stochastic gradient descent algorithms (Async-MSGD) is one of the most popular algorithms in distributed machine learning.
A Diffusion Approximation Theory of Momentum SGD in Nonconvex Optimization
Our theoretical discovery partially corroborates the empirical success of MSGD in training deep neural networks.
