Saxe, Andrew M.

31 publications

ICLR 2025 A Theory of Initialisation's Impact on Specialisation Devon Jarvis, Sebastian Lee, Clémentine Carla Juliette Dominé, Andrew M Saxe, Stefano Sarao Mannelli

ICML 2025 Algorithm Development in Neural Networks: Insights from the Streaming Parity Task Loek Van Rossem, Andrew M Saxe

ICLRW 2025 Distinct Computations Emerge from Compositional Curricula in In-Context Learning Jin Hwa Lee, Andrew Kyle Lampinen, Aaditya K Singh, Andrew M Saxe

ICLR 2025 From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks Clémentine Carla Juliette Dominé, Nicolas Anguita, Alexandra Maria Proca, Lukas Braun, Daniel Kunin, Pedro A. M. Mediano, Andrew M Saxe

ICLR 2025 Make Haste Slowly: A Theory of Emergent Structured Mixed Selectivity in Feature Learning ReLU Networks Devon Jarvis, Richard Klein, Benjamin Rosman, Andrew M Saxe

NeurIPS 2025 Memory by Accident: A Theory of Learning as a Byproduct of Network Stabilization Basile Confavreux, Will Dorrell, Nishil Patel, Andrew M Saxe

ICML 2025 Not All Solutions Are Created Equal: An Analytical Dissociation of Functional and Representational Similarity in Deep Linear Neural Networks Lukas Braun, Erin Grant, Andrew M Saxe

ICML 2025 Strategy Coopetition Explains the Emergence and Transience of In-Context Learning Aaditya K Singh, Ted Moskovitz, Sara Dragutinović, Felix Hill, Stephanie C.Y. Chan, Andrew M Saxe

ICML 2025 Training Dynamics of In-Context Learning in Linear Attention Yedi Zhang, Aaditya K Singh, Peter E. Latham, Andrew M Saxe

TMLR 2025 When Are Bias-Free ReLU Networks Effectively Linear Networks? Yedi Zhang, Andrew M Saxe, Peter E. Latham

NeurIPSW 2024 A Linear Network Theory of Iterated Learning Devon Jarvis, Richard Klein, Benjamin Rosman, Andrew M Saxe

NeurIPSW 2024 A Theory of Initialisation's Impact on Specialisation Devon Jarvis, Sebastian Lee, Clémentine Carla Juliette Dominé, Andrew M Saxe, Stefano Sarao Mannelli

NeurIPS 2024 Flexible Task Abstractions Emerge in Linear Networks with Fast and Bounded Units Kai Sandbrink, Jan P. Bauer, Alexandra M. Proca, Andrew M. Saxe, Christopher Summerfield, Ali Hummos

NeurIPSW 2024 From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks Clémentine Carla Juliette Dominé, Nicolas Anguita, Alexandra Maria Proca, Lukas Braun, Daniel Kunin, Pedro A. M. Mediano, Andrew M Saxe

NeurIPSW 2024 From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks Clémentine Carla Juliette Dominé, Nicolas Anguita, Alexandra Maria Proca, Lukas Braun, Daniel Kunin, Pedro A. M. Mediano, Andrew M Saxe

ICMLW 2024 Get Rich Quick: Exact Solutions Reveal How Unbalanced Initializations Promote Rapid Feature Learning Daniel Kunin, Allan Raventos, Clémentine Carla Juliette Dominé, Feng Chen, David Klindt, Andrew M Saxe, Surya Ganguli

ICML 2024 Tilting the Odds at the Lottery: The Interplay of Overparameterisation and Curricula in Neural Networks Stefano Sarao Mannelli, Yaraslau Ivashynka, Andrew M Saxe, Luca Saglietti

ICML 2024 Understanding Unimodal Bias in Multimodal Deep Linear Networks Yedi Zhang, Peter E. Latham, Andrew M Saxe

ICML 2024 What Needs to Go Right for an Induction Head? a Mechanistic Study of In-Context Learning Circuits and Their Formation Aaditya K Singh, Ted Moskovitz, Felix Hill, Stephanie C.Y. Chan, Andrew M Saxe

ICMLW 2024 When Are Bias-Free ReLU Networks like Linear Networks? Yedi Zhang, Andrew M Saxe, Peter E. Latham

ICML 2024 When Representations Align: Universality in Representation Learning Dynamics Loek Van Rossem, Andrew M Saxe

ICML 2024 Why Do Animals Need Shaping? a Theory of Task Composition and Curriculum Learning Jin Hwa Lee, Stefano Sarao Mannelli, Andrew M Saxe

ICLR 2023 On the Specialization of Neural Modules Devon Jarvis, Richard Klein, Benjamin Rosman, Andrew M Saxe

ICLRW 2023 The Rl Perceptron: Dynamics of Policy Learning in High Dimensions Nishil Patel, Sebastian Lee, Stefano Sarao Mannelli, Sebastian Goldt, Andrew M Saxe

NeurIPS 2019 Dynamics of Stochastic Gradient Descent for Two-Layer Neural Networks in the Teacher-Student Setup Sebastian Goldt, Madhu Advani, Andrew M Saxe, Florent Krzakala, Lenka Zdeborová

ICLR 2018 Hierarchical Subtask Discovery with Non-Negative Matrix Factorization Adam C. Earle, Andrew M. Saxe, Benjamin Rosman

ICML 2017 Hierarchy Through Composition with Multitask LMDPs Andrew M. Saxe, Adam C. Earle, Benjamin Rosman

NeurIPS 2016 Tensor Switching Networks Chuan-Yung Tsai, Andrew M Saxe, Andrew M Saxe, David Cox

NeurIPS 2016 Tensor Switching Networks Chuan-Yung Tsai, Andrew M Saxe, Andrew M Saxe, David Cox

ICLR 2014 Exact Solutions to the Nonlinear Dynamics of Learning in Deep Linear Neural Networks Andrew M. Saxe, James L. McClelland, Surya Ganguli

ICML 2011 On Random Weights and Unsupervised Feature Learning Andrew M. Saxe, Pang Wei Koh, Zhenghao Chen, Maneesh Bhand, Bipin Suresh, Andrew Y. Ng