Boaz Barak
14 papers · 2016–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+7 more ↓ Show less ↑
π Academic Marathon (9) π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (5) π Cross-Pollinator (13)
π
Academic Marathon
(9)
πΊοΈ
Taxonomy Completionist
(19)
π
Cross-Pollinator
(13)
π
Triple Crown
π§¬
Topic Evolution
π₯
Unstoppable
(7)
π
Century Club
(14)
Conferences
NIPS (5)
ICML (4)
ICLR (3)
COLT (1)
JMLR (1)
Top co-authors
Research topics
Keywords
stochastic gradient descent
(3)
data repetition
(2)
graph matching
(1)
graph theory
(1)
hypothesis testing
(1)
sample complexity
(1)
neural network optimization
(1)
nuclear norm
(1)
computational complexity
(1)
token efficiency
(1)
fourier analysis
(1)
mutual information
(1)
neural representation
(1)
tensor completion
(1)
neural network training
(1)
generative model
(1)
linear classifier
(1)
diffusion model
(1)
phase transition
(1)
learning theory
(1)
Papers
Scaling Data-Constrained Language Models
JMLR 2025
Watermarks in the Sand: Impossibility of Strong Watermarking for Language Models
ICML 2024
Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning
ICML 2024
Distinguishing the Knowable from the Unknowable with Language Models
ICML 2024
Scaling Data-Constrained Language Models
NIPS 2023
On Provable Copyright Protection for Generative Models
ICML 2023
Deconstructing Distributions: A Pointwise Framework of Learning
ICLR 2023
Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit
NIPS 2022
For self-supervised learning, Rationality implies generalization, provably
ICLR 2021
Revisiting Model Stitching to Compare Neural Representations
NIPS 2021
Deep Double Descent: Where Bigger Models and More Data Hurt
ICLR 2020
(Nearly) Efficient Algorithms for the Graph Matching Problem on Correlated Random Graphs
NIPS 2019
SGD on Neural Networks Learns Functions of Increasing Complexity
NIPS 2019
Noisy Tensor Completion via the Sum-of-Squares Hierarchy
COLT 2016