Emmanuel Abbe
27 papers · 2015–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+13 more ↓ Show less ↑
π Academic Marathon (10) π Conference Polyglot (5) π Interdisciplinary Bridge π§ Keyword Pioneer π£ Hot Topic Early Bird
π
Cross-Pollinator
(8)
πΊοΈ
Taxonomy Completionist
(41)
π
Conference Polyglot
(5)
π§¬
Topic Evolution
π¬
Deep Specialist
(16)
π
Keyword Champion
(3)
π
Triple Crown
ποΈ
Keyword Collector
(94)
β‘
Prolific Year
(5)
π
Century Club
(27)
π₯
Unstoppable
(6)
π
Trend Setter
β
The Questioner
(2)
Conferences
NIPS (13)
ICML (5)
JMLR (4)
COLT (3)
ICLR (2)
Top co-authors
Keywords
neural network
(9)
gradient descent
(6)
stochastic gradient descent
(5)
learning theory
(5)
community detection
(4)
stochastic block model
(4)
curriculum learning
(3)
out-of-distribution generalization
(3)
boolean function
(3)
belief propagation
(3)
influence maximization
(2)
generalization error
(2)
graph clustering
(2)
generalization bound
(2)
sample complexity
(2)
vc dimension
(2)
differentiable learning
(2)
neural network optimization
(2)
deep learning
(2)
information theory
(2)
Papers
Learning High-Degree Parities: The Crucial Role of the Initialization
ICLR 2025
On the Minimal Degree Bias in Generalization on the Unseen for non-Boolean Functions
ICML 2024
When can transformers reason with abstract symbols?
ICLR 2024
Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalization
NIPS 2024
How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad
NIPS 2024
Generalization on the Unseen, Logic Reasoning and Degree Curriculum
JMLR 2024
Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputs
NIPS 2023
SGD learning on neural networks: leap complexity and saddle-to-saddle dynamics
COLT 2023
Generalization on the Unseen, Logic Reasoning and Degree Curriculum
ICML 2023
Transformers learn through gradual rank increase
NIPS 2023
Learning to Reason with Neural Networks: Generalization, Unseen Data and Boolean Measures
NIPS 2022
An Initial Alignment between Neural Network and Target is Needed for Gradient Descent to Learn
ICML 2022
The merged-staircase property: a necessary and nearly sufficient condition for SGD learning of sparse functions on two-layer neural networks
COLT 2022
On the non-universality of deep learning: quantifying the cost of symmetry
NIPS 2022
Stochastic block model entropy and broadcasting on trees with survey
COLT 2021
On the Power of Differentiable Learning versus PAC and SQ Learning
NIPS 2021
The staircase property: How hierarchical structure can guide deep learning
NIPS 2021
Quantifying the Benefit of Using Differentiable Learning over Tangent Kernels
ICML 2021
Generalized Nonbacktracking Bounds on the Influence
JMLR 2020
Chaining Meets Chain Rule: Multilevel Entropic Regularization and Training of Neural Networks
JMLR 2020
On the universality of deep learning
NIPS 2020
Chaining Mutual Information and Tightening Generalization Bounds
NIPS 2018
Communication-Computation Efficient Gradient Coding
ICML 2018
Community Detection and Stochastic Block Models: Recent Developments
JMLR 2018
Nonbacktracking Bounds on the Influence in Independent Cascade Models
NIPS 2017
Achieving the KS threshold in the general stochastic block model with linearized acyclic belief propagation
NIPS 2016
Recovering Communities in the General Stochastic Block Model Without Knowing the Parameters
NIPS 2015