Andrew M Saxe
~Andrew_M_Saxe1
17
论文总数
8.5
年均投稿
平均评分
接收情况11/17
会议分布
ICLR
9
ICML
4
NeurIPS
4
发表论文 (17 篇)
202510 篇
4
Algorithm Development in Neural Networks: Insights from the Streaming Parity Task
ICML 2025Oral
4
When Are Bias-Free ReLU Networks Effectively Linear Networks?
ICLR 2025Rejected
4
Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networks
ICML 2025Spotlight
4
Early learning of the optimal constant solution in neural networks and humans
ICLR 2025Rejected
4
Make Haste Slowly: A Theory of Emergent Structured Mixed Selectivity in Feature Learning ReLU Networks
ICLR 2025Poster
4
Memory by accident: a theory of learning as a byproduct of network stabilization
NeurIPS 2025Poster
4
Training Dynamics of In-Context Learning in Linear Attention
ICML 2025Spotlight
4
A Theory of Initialisation's Impact on Specialisation
ICLR 2025Poster
3
Strategy Coopetition Explains the Emergence and Transience of In-Context Learning
ICML 2025Oral
3
From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks
ICLR 2025Poster
20247 篇
3
Nonlinear dynamics of localization in neural receptive fields
NeurIPS 2024Spotlight
4
A Theory of Unimodal Bias in Multimodal Learning
ICLR 2024Rejected
4
Meta-Learning Strategies through Value Maximization in Neural Networks
ICLR 2024Rejected
3
Flexible task abstractions emerge in linear networks with fast and bounded units
NeurIPS 2024Spotlight
-
The RL Perceptron: Generalisation Dynamics of Policy Learning in High Dimensions
ICLR 2024withdrawn
4
Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning
NeurIPS 2024Spotlight
3
Full Elastic Weight Consolidation via the Surrogate Hessian-Vector Product
ICLR 2024withdrawn