Optimization
Smoothed Analysis of Sequential Probability Assignment
Our approach establishes a general-purpose reduction from minimax rates for sequential probability assignment for smoothed adversaries to minimax rates for transductive learning. This leads to optimal (logarithmic) fast rates for parametric classes and classes with finite VC dimension.
Faster Differentially Private Convex Optimization via Second-Order Methods
We first develop a private variant of the regularized cubic Newton method of Nesterov and Polyak [NP06], and show that for the class of strongly convex loss functions, our algorithm has quadratic convergence and achieves the optimal excess loss.
Human-in-the-Loop Optimization for Deep Stimulus Encoding in Visual Prostheses
However, patient outcomes with current technologies are limited.
Self-Correcting Bayesian Optimization through Bayesian Active Learning
Gaussian processes are the model of choice in Bayesian optimization and active learning.
Accelerating Motion Planning via Optimal Transport
Motion planning is still an open problem for many disciplines, e.g., robotics, autonomous driving, due to their need for high computational resources that hinder
BQ-NCO: Bisimulation Quotienting for Efficient Neural Combinatorial Optimization
Despite the success of neural-based combinatorial optimization methods for end-to-end heuristic learning, out-of-distribution generalization remains a challenge.
Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods
We list each algorithm's effective stepsize at iteration