Andrew M Saxe
16 papers · 2016–2025 · 3 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 ↓+6 more ↓ Show less ↑
🗺️ Taxonomy Completionist (19) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🐣 Hot Topic Early Bird
🔬
Deep Specialist
(12)
🏆
Keyword Champion
⚡
Prolific Year · Productive
❓
The Questioner
(2)
🗃️
Keyword Collector
(81)
💎
Century Club · Bronze
Venues
Top co-authors
Research topics
Machine Learning
(15)
Optimization & Theory
(13)
Deep Learning
(11)
Architectures
(10)
Core Methods
(5)
Artificial Intelligence
(4)
Core AI
(4)
Learning Types · Machine Learning
(4)
Techniques
(2)
Natural Language Processing
(1)
Reinforcement Learning
(1)
Learning Types · Deep Learning
(1)
Methods
(1)
Resources & Methods
(1)
Keywords
neural network
(3)
learning theory
(2)
weight initialization
(2)
continual learning
(2)
subcircuits
(2)
modular architecture
(2)
representation learning
(2)
learning dynamics
(2)
curriculum learning
(2)
in-context learning
(2)
stochastic gradient descent
(1)
gradient descent
(1)
generalization error
(1)
principal component regression
(1)
neural network optimization
(1)
catastrophic forgetting
(1)
recurrent neural network
(1)
online learning
(1)
latent representation
(1)
phase transition
(1)
Papers
Algorithm Development in Neural Networks: Insights from the Streaming Parity Task
ICML 2025
A Theory of Initialisation's Impact on Specialisation
ICLR 2025
From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks
ICLR 2025
Make Haste Slowly: A Theory of Emergent Structured Mixed Selectivity in Feature Learning ReLU Networks
ICLR 2025
Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks
ICML 2025
Strategy Coopetition Explains the Emergence and Transience of In-Context Learning
ICML 2025
Training Dynamics of In-Context Learning in Linear Attention
ICML 2025
Flexible task abstractions emerge in linear networks with fast and bounded units
NeurIPS 2024
Tilting the Odds at the Lottery: the Interplay of Overparameterisation and Curricula in Neural Networks
ICML 2024
Understanding Unimodal Bias in Multimodal Deep Linear Networks
ICML 2024
What needs to go right for an induction head? A mechanistic study of in-context learning circuits and their formation
ICML 2024
When Representations Align: Universality in Representation Learning Dynamics
ICML 2024
Why Do Animals Need Shaping? A Theory of Task Composition and Curriculum Learning
ICML 2024
On The Specialization of Neural Modules
ICLR 2023
Dynamics of stochastic gradient descent for two-layer neural networks in the teacher-student setup
NeurIPS 2019
Tensor Switching Networks
NeurIPS 2016