Sholom Schechtman
3 papers · 2023–2025 · 2 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(10)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
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)
critical point
(1)
quantized neural network
(1)
stiefel manifold
(1)
projection method
(1)
stochastic subgradient descent
(1)
constrained gradient method
(1)
homogeneous neural network
(1)
conservative field flow
(1)
normalized classification margin
(1)
model compression
(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