Gal Kaplun
7 papers · 2019–2024 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge π Academic Marathon (5) π Cross-Pollinator (15) π Conference Polyglot (3) πΊοΈ Taxonomy Completionist (11)
π§
Keyword Pioneer
π₯
Unstoppable
(6)
Conferences
ICLR (3)
ICML (2)
NIPS (2)
Top co-authors
Keywords
stochastic gradient descent
(1)
robust optimization
(1)
knowledge distillation
(1)
mutual information
(1)
influence maximization
(1)
linear classifier
(1)
social network
(1)
bayes optimal classifier
(1)
student network
(1)
conditional sampling
(1)
kernel machine
(1)
classification task
(1)
independent cascade model
(1)
multiplicative weight update
(1)
overparameterized regime
(1)
neural network
(1)
over-parameterized regime
(1)
hyperparametric model
(1)
conditional sampler
(1)
Papers
Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning
ICML 2024
Deconstructing Distributions: A Pointwise Framework of Learning
ICLR 2023
Knowledge Distillation: Bad Models Can Be Good Role Models
NIPS 2022
For self-supervised learning, Rationality implies generalization, provably
ICLR 2021
Deep Double Descent: Where Bigger Models and More Data Hurt
ICLR 2020
SGD on Neural Networks Learns Functions of Increasing Complexity
NIPS 2019
Robust Influence Maximization for Hyperparametric Models
ICML 2019