Sholom Schechtman
3 papers · 2023–2025 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🐣
Hot Topic Early Bird
🌍
Conference Polyglot
(2)
🐝
Cross-Pollinator
(9)
Conferences
COLT (2)
AISTATS (1)
Top co-authors
Keywords
stochastic optimization
(2)
stochastic gradient descent
(1)
neural network training
(1)
non-convex optimization
(1)
neural network optimization
(1)
constrained optimization
(1)
gradient descent
(1)
oracle complexity
(1)
manifold optimization
(1)
weight quantization
(1)
quantized neural network
(1)
model compression
(1)
stiefel manifold
(1)
Papers
The late-stage training dynamics of (stochastic) subgradient descent on homogeneous neural networks
COLT 2025
ASkewSGD : An Annealed interval-constrained Optimisation method to train Quantized Neural Networks
AISTATS 2023
Orthogonal Directions Constrained Gradient Method: from non-linear equality constraints to Stiefel manifold
COLT 2023