Nikita Puchkin
9 papers · 2021–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot · Bronze 🏃 Academic Marathon · Sprint 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (21) 🔥 Unstoppable · Bronze
🗃️
Keyword Collector
(59)
Venues
Top co-authors
Research topics
Keywords
excess risk
(2)
convergence rate
(2)
active learning
(1)
model misspecification
(1)
density estimation
(1)
optimal transport
(1)
covariance estimation
(1)
distribution shift
(1)
high-dimensional statistics
(1)
empirical risk minimization
(1)
intrinsic dimension
(1)
nonparametric estimation
(1)
agnostic learning
(1)
generalization error
(1)
variance reduction
(1)
minimax optimality
(1)
contrastive learning
(1)
exp-concave loss
(1)
stochastic convex optimization
(1)
stochastic optimization
(1)
Papers
Approximation Rates for Schrödinger Bridge Potentials via Fixed-Point ERM
UAI 2026
Generalization error bound for denoising score matching under relaxed manifold assumption
COLT 2025
Breaking the Heavy-Tailed Noise Barrier in Stochastic Optimization Problems
AISTATS 2024
Dimension-free Structured Covariance Estimation
COLT 2024
Rates of convergence for density estimation with generative adversarial networks
JMLR 2024
A Contrastive Approach to Online Change Point Detection
AISTATS 2023
Exploring Local Norms in Exp-concave Statistical Learning
COLT 2023
Structure-adaptive Manifold Estimation
JMLR 2022
Exponential savings in agnostic active learning through abstention
COLT 2021