Search Results for author:
Found 8 papers, 1 papers with code
Approximating a linear dynamical system from non-sequential data
Given non-sequential snapshots from instances of a dynamical system, we design a compressed sensing based algorithm that reconstructs the dynamical system.
Enhancing selectivity using Wasserstein distance based reweighing
Given two labeled data-sets $\mathcal{S}$ and $\mathcal{T}$, we design a simple and efficient greedy algorithm to reweigh the loss function such that the limiting distribution of the neural network weights that result from training on $\mathcal{S}$ approaches the limiting distribution that would have resulted by training on $\mathcal{T}$.
Learning Rate Schedules in the Presence of Distribution Shift
We design learning rate schedules that minimize regret for SGD-based online learning in the presence of a changing data distribution.
Learning to Price Against a Moving Target
In the Learning to Price setting, a seller posts prices over time with the goal of maximizing revenue while learning the buyer's valuation.
Limiting Behaviors of Nonconvex-Nonconcave Minimax Optimization via Continuous-Time Systems
Unlike nonconvex optimization, where gradient descent is guaranteed to converge to a local optimizer, algorithms for nonconvex-nonconcave minimax optimization can have topologically different solution paths: sometimes converging to a solution, sometimes never converging and instead following a limit cycle, and sometimes diverging.
The Landscape of the Proximal Point Method for Nonconvex-Nonconcave Minimax Optimization
Critically, we show this envelope not only smooths the objective but can convexify and concavify it based on the level of interaction present between the minimizing and maximizing variables.
The Spectrum of the Fisher Information Matrix of a Single-Hidden-Layer Neural Network
An important factor contributing to the success of deep learning has been the remarkable ability to optimize large neural networks using simple first-order optimization algorithms like stochastic gradient descent.
Nonlinear random matrix theory for deep learning
Neural network configurations with random weights play an important role in the analysis of deep learning.
