Alireza Mousavi-Hosseini
7 papers · 2023–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🌍 Conference Polyglot (3) 🐝 Cross-Pollinator (3) 🗺️ Taxonomy Completionist (13)
📈
Trend Setter
Conferences
ICLR (3)
NIPS (3)
COLT (1)
Top co-authors
Research topics
Keywords
sampling algorithm
(2)
convergence rate
(2)
bayesian inference
(1)
sample complexity
(1)
markov chain monte carlo
(1)
monte carlo sampling
(1)
stochastic process
(1)
oracle complexity
(1)
bilevel optimization
(1)
heavy-tailed distribution
(1)
stable distribution
(1)
single index model
(1)
langevin monte carlo
(1)
heavy-tailed sampling
(1)
chi-squared divergence
(1)
proximal sampler
(1)
stable oracle
(1)
high-accuracy guarantee
(1)
stochastic method
(1)
langevin diffusion
(1)
Papers
Robust Feature Learning for Multi-Index Models in High Dimensions
ICLR 2025
Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics
ICLR 2025
A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers
NIPS 2024
Mean-Field Langevin Dynamics for Signed Measures via a Bilevel Approach
NIPS 2024
Towards a Complete Analysis of Langevin Monte Carlo: Beyond Poincaré Inequality
COLT 2023
Gradient-Based Feature Learning under Structured Data
NIPS 2023
Neural Networks Efficiently Learn Low-Dimensional Representations with SGD
ICLR 2023