Boaz Barak
14 papers · 2016–2025 · 5 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 ↓+5 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (26) π Conference Polyglot Β· Silver π£ Hot Topic Early Bird π Academic Marathon Β· Sprint
π
Triple Crown
π
Renaissance Researcher
(5)
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(77)
Venues
Top co-authors
Research topics
Machine Learning
(10)
Optimization & Theory
(7)
Core Methods
(5)
Deep Learning
(4)
Natural Language Processing
(4)
Artificial Intelligence
(3)
Mathematics & Optimization
(3)
Core AI
(3)
Generation
(3)
Learning Types
(3)
Optimization
(3)
Mathematics
(2)
Techniques
(2)
Computer Science
(1)
Security & Privacy
(1)
Keywords
stochastic gradient descent
(3)
data repetition
(2)
learning theory
(2)
representation learning
(2)
sample complexity
(1)
graph theory
(1)
online learning
(1)
tensor completion
(1)
epistemic uncertainty
(1)
self-supervised learning
(1)
embedding
(1)
fourier analysis
(1)
neural network optimization
(1)
computational complexity
(1)
hypothesis testing
(1)
token efficiency
(1)
mutual information
(1)
neural representation
(1)
graph matching
(1)
neural network training
(1)
Papers
Scaling Data-Constrained Language Models
JMLR 2025
Beyond Implicit Bias: The Insignificance of SGD Noise in Online Learning
ICML 2024
Distinguishing the Knowable from the Unknowable with Language Models
ICML 2024
Watermarks in the Sand: Impossibility of Strong Watermarking for Language Models
ICML 2024
Deconstructing Distributions: A Pointwise Framework of Learning
ICLR 2023
On Provable Copyright Protection for Generative Models
ICML 2023
Scaling Data-Constrained Language Models
NeurIPS 2023
Hidden Progress in Deep Learning: SGD Learns Parities Near the Computational Limit
NeurIPS 2022
For self-supervised learning, Rationality implies generalization, provably
ICLR 2021
Revisiting Model Stitching to Compare Neural Representations
NeurIPS 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
NeurIPS 2019
SGD on Neural Networks Learns Functions of Increasing Complexity
NeurIPS 2019
Noisy Tensor Completion via the Sum-of-Squares Hierarchy
COLT 2016