Nisheeth Vishnoi
where else to find them
bluesky:nisheethvishnoi.bsky.social
what they talk about
where they keep going back
no series more than once — all 5 in the filters
on a stage with
never shared a talk
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Computationally Efficient Alternatives to Nonconvex-Nonconcave Min-Max Optimization | Adversarial Approaches in Machine Learning 2022 | 2022-02-17 |
Proposes a new solution concept called epsilon-greedy adversarial equilibrium that limits the maximizer to greedy paths and proves such equilibria exist for… | ||
| An Introduction to Hamiltonian Monte Carlo Method for Sampling | Geometric Methods in Optimization and Sampling Boot Camp | 2021-08-30 |
Algorithm samples by drawing a Gaussian momentum, simulating Hamiltonian flow for time T, then refreshing momentum; it removes the Metropolis accept/reject in… | ||
| Optimization and Sampling Under Symmetry: Part 1 -- Examples | Geometric Methods in Optimization and Sampling Boot Camp | 2021-08-30 |
Starts from two concrete claims: minimizing vAv over the complex unit sphere equals the matrix's smallest eigenvalue by recasting rank‑one projections as a… | ||
| Entropy, Capacity, and Counting | Deterministic Counting, Probability, and Zeros of Partition Functions (Simons Institute workshop, 2019) | 2019-03-18 |
Generalizes Gurvits' capacity to compute sums of polynomial coefficients over a polytope and gives a concrete algorithmic claim: with an oracle to evaluate the… | ||
| Subdeterminant Maximization via Nonconvex Relaxations and Anti-concentration | Discrete Optimization via Continuous Relaxation | 2017-09-11 |
Presents randomized algorithms that actually output sets for constrained subdeterminant maximization over regular matroids and partition matroids, using a… | ||
| Faster Spectral Algorithms via Approximation Theory | Fast Algorithms via Spectral Methods 2014 | 2014-12-01 |
Uniform polynomial approximations turn matrix powers into O(M · D) work and give X^S approximants of degree about sqrt(S)·log(1/δ), so S-step walks and… | ||
| nothing matches | ||