Haim Sompolinsky
7 papers · 2010–2025 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π£ Hot Topic Early Bird π Interdisciplinary Bridge πΊοΈ Taxonomy Completionist (17) π Renaissance Researcher (5) π§ Keyword Pioneer
π
Conference Polyglot
(2)
π
Academic Marathon
(15)
π
Cross-Pollinator
(13)
π
Keyword Champion
π
Trend Setter
Conferences
NIPS (6)
ICLR (1)
Top co-authors
Research topics
Keywords
neural network optimization
(2)
statistical mechanics
(2)
bayesian learning
(2)
network architecture
(1)
principal component analysis
(1)
attention mechanism
(1)
subspace analysis
(1)
network dynamics
(1)
input-evoked responses
(1)
theoretical analysis
(1)
sensory processing
(1)
gradient descent
(1)
kernel combination
(1)
short-term memory
(1)
neural network dynamics
(1)
synaptic memory
(1)
input selectivity
(1)
spontaneous activity
(1)
network pruning
(1)
compressed sensing
(1)
Papers
When narrower is better: the narrow width limit of Bayesian parallel branching neural networks
ICLR 2025
Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers
NIPS 2024
A theory of weight distribution-constrained learning
NIPS 2022
Globally Gated Deep Linear Networks
NIPS 2022
Optimal Architectures in a Solvable Model of Deep Networks
NIPS 2016
Inferring Stimulus Selectivity from the Spatial Structure of Neural Network Dynamics
NIPS 2010
Short-term memory in neuronal networks through dynamical compressed sensing
NIPS 2010