Daniel Kunin - RankMe

23 papers A* 9Journal 14

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Sequential Group Composition: A Window into the Mechanics of Deep Learning. CoRR Giovanni Luca Marchetti, Daniel Kunin, Adele Myers, Francisco Acosta, Nina Miolane
2026	J	`jnl`	Symmetry Breaking in Transformers for Efficient and Interpretable Training. CoRR Eva Silverstein, Daniel Kunin, Vasudev Shyam
2025	J	`jnl`	Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks. CoRR Daniel Kunin, Giovanni Luca Marchetti, Feng Chen, Dhruva Karkada, James B. Simon, Michael Robert DeWeese, Surya Ganguli, Nina Miolane
2025	A*	`conf`	From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks. ICLR Clémentine Carla Juliette Dominé, Nicolas Anguita, Alexandra Maria Proca, Lukas Braun, Daniel Kunin, Pedro A. M. Mediano, Andrew M. Saxe
2024	J	`jnl`	From Lazy to Rich: Exact Learning Dynamics in Deep Linear Networks. CoRR Clémentine C. J. Dominé, Nicolas Anguita, Alexandra Maria Proca, Lukas Braun, Daniel Kunin, Pedro A. M. Mediano, Andrew M. Saxe
2024	A*	`conf`	Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning. NeurIPS Daniel Kunin, Allan Raventós, Clémentine C. J. Dominé, Feng Chen, David A. Klindt, Andrew M. Saxe, Surya Ganguli
2024	J	`jnl`	Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning. CoRR Daniel Kunin, Allan Raventós, Clémentine C. J. Dominé, Feng Chen, David A. Klindt, Andrew M. Saxe, Surya Ganguli
2024	J	`jnl`	The Limiting Dynamics of SGD: Modified Loss, Phase-Space Oscillations, and Anomalous Diffusion. Neural Comput. Daniel Kunin, Javier Sagastuy-Breña, Lauren E. Gillespie, Eshed Margalit, Hidenori Tanaka, Surya Ganguli, Daniel L. K. Yamins
2023	A*	`conf`	Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks. NeurIPS Feng Chen, Daniel Kunin, Atsushi Yamamura, Surya Ganguli
2023	J	`jnl`	Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks. CoRR Feng Chen, Daniel Kunin, Atsushi Yamamura, Surya Ganguli
2023	A*	`conf`	The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks. ICLR Daniel Kunin, Atsushi Yamamura, Chao Ma, Surya Ganguli
2022	J	`jnl`	The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks. CoRR Daniel Kunin, Atsushi Yamamura, Chao Ma, Surya Ganguli
2021	A*	`conf`	Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics. ICLR Daniel Kunin, Javier Sagastuy-Breña, Surya Ganguli, Daniel L. K. Yamins, Hidenori Tanaka
2021	A*	`conf`	Noether's Learning Dynamics: Role of Symmetry Breaking in Neural Networks. NeurIPS Hidenori Tanaka, Daniel Kunin
2021	J	`jnl`	Noether's Learning Dynamics: The Role of Kinetic Symmetry Breaking in Deep Learning. CoRR Hidenori Tanaka, Daniel Kunin
2021	J	`jnl`	Rethinking the limiting dynamics of SGD: modified loss, phase space oscillations, and anomalous diffusion. CoRR Daniel Kunin, Javier Sagastuy-Breña, Lauren E. Gillespie, Eshed Margalit, Hidenori Tanaka, Surya Ganguli, Daniel L. K. Yamins
2020	J	`jnl`	Neural Mechanics: Symmetry and Broken Conservation Laws in Deep Learning Dynamics. CoRR Daniel Kunin, Javier Sagastuy-Breña, Surya Ganguli, Daniel L. K. Yamins, Hidenori Tanaka
2020	A*	`conf`	Pruning neural networks without any data by iteratively conserving synaptic flow. NeurIPS Hidenori Tanaka, Daniel Kunin, Daniel L. K. Yamins, Surya Ganguli
2020	J	`jnl`	Pruning neural networks without any data by iteratively conserving synaptic flow. CoRR Hidenori Tanaka, Daniel Kunin, Daniel L. K. Yamins, Surya Ganguli
2020	A*	`conf`	Two Routes to Scalable Credit Assignment without Weight Symmetry. ICML Daniel Kunin, Aran Nayebi, Javier Sagastuy-Breña, Surya Ganguli, Jonathan M. Bloom, Daniel Yamins
2020	J	`jnl`	Two Routes to Scalable Credit Assignment without Weight Symmetry. CoRR Daniel Kunin, Aran Nayebi, Javier Sagastuy-Breña, Surya Ganguli, Jonathan M. Bloom, Daniel L. K. Yamins
2019	A*	`conf`	Loss Landscapes of Regularized Linear Autoencoders. ICML Daniel Kunin, Jonathan M. Bloom, Aleksandrina Goeva, Cotton Seed
2019	J	`jnl`	Loss Landscapes of Regularized Linear Autoencoders. CoRR Daniel Kunin, Jonathan M. Bloom, Aleksandrina Goeva, Cotton Seed