Jason Altschuler
9 papers · 2016–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
๐บ๏ธ Taxonomy Completionist (24) ๐งญ Keyword Pioneer ๐ Conference Polyglot (4) ๐ Academic Marathon (8) ๐ฃ Hot Topic Early Bird
๐
Cross-Pollinator
(11)
๐
Renaissance Researcher
(6)
๐
Interdisciplinary Bridge
๐งฌ
Topic Evolution
๐
Trend Setter
Conferences
NIPS (4)
COLT (2)
ICML (2)
JMLR (1)
Top co-authors
Keywords
optimal transport
(4)
multi-armed bandit
(2)
differential privacy
(1)
stochastic gradient descent
(1)
online learning
(1)
feature selection
(1)
robust statistics
(1)
best arm identification
(1)
sample complexity
(1)
gradient descent
(1)
renyi divergence
(1)
matrix approximation
(1)
coordinate descent
(1)
markov chain
(1)
stationary distribution
(1)
langevin dynamics
(1)
nystrรถm method
(1)
concentration inequality
(1)
mixing time
(1)
wasserstein distance
(1)
Papers
Shifted Interpolation for Differential Privacy
ICML 2024
Resolving the Mixing Time of the Langevin Algorithm to its Stationary Distribution for Log-Concave Sampling
COLT 2023
Privacy of Noisy Stochastic Gradient Descent: More Iterations without More Privacy Loss
NIPS 2022
Averaging on the Bures-Wasserstein manifold: dimension-free convergence of gradient descent
NIPS 2021
Massively scalable Sinkhorn distances via the Nystrรถm method
NIPS 2019
Best Arm Identification for Contaminated Bandits
JMLR 2019
Online learning over a finite action set with limited switching
COLT 2018
Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration
NIPS 2017
Greedy Column Subset Selection: New Bounds and Distributed Algorithms
ICML 2016