Niru Maheswaranathan

38 papers A* 11Journal 21Unranked 6

Year	Rank	Type	Title / Venue / Authors
2022	—	`conf`	Practical Tradeoffs between Memory, Compute, and Performance in Learned Optimizers. CoLLAs Luke Metz, C. Daniel Freeman, James Harrison, Niru Maheswaranathan, Jascha Sohl-Dickstein
2022	J	`jnl`	Practical tradeoffs between memory, compute, and performance in learned optimizers. CoRR Luke Metz, C. Daniel Freeman, James Harrison, Niru Maheswaranathan, Jascha Sohl-Dickstein
2021	—	`conf`	A mechanistically interpretable model of the retinal neural code for natural scenes with multiscale adaptive dynamics. ACSCC Xuehao Ding, Dongsoo Lee, Satchel Grant, Heike Stein, Lane McIntosh, Niru Maheswaranathan, Stephen Baccus
2021	A*	`conf`	Reverse engineering learned optimizers reveals known and novel mechanisms. NeurIPS Niru Maheswaranathan, David Sussillo, Luke Metz, Ruoxi Sun, Jascha Sohl-Dickstein
2021	A*	`conf`	The geometry of integration in text classification RNNs. ICLR Kyle Aitken, Vinay Venkatesh Ramasesh, Ankush Garg, Yuan Cao, David Sussillo, Niru Maheswaranathan
2021	J	`jnl`	Training Learned Optimizers with Randomly Initialized Learned Optimizers. CoRR Luke Metz, C. Daniel Freeman, Niru Maheswaranathan, Jascha Sohl-Dickstein
2021	A*	`conf`	Understanding How Encoder-Decoder Architectures Attend. NeurIPS Kyle Aitken, Vinay V. Ramasesh, Yuan Cao, Niru Maheswaranathan
2021	J	`jnl`	Understanding How Encoder-Decoder Architectures Attend. CoRR Kyle Aitken, Vinay V. Ramasesh, Yuan Cao, Niru Maheswaranathan
2020	A*	`conf`	How recurrent networks implement contextual processing in sentiment analysis. ICML Niru Maheswaranathan, David Sussillo
2020	J	`jnl`	How recurrent networks implement contextual processing in sentiment analysis. CoRR Niru Maheswaranathan, David Sussillo
2020	J	`jnl`	Reverse engineering learned optimizers reveals known and novel mechanisms. CoRR Niru Maheswaranathan, David Sussillo, Luke Metz, Ruoxi Sun, Jascha Sohl-Dickstein
2020	J	`jnl`	Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves. CoRR Luke Metz, Niru Maheswaranathan, C. Daniel Freeman, Ben Poole, Jascha Sohl-Dickstein
2020	J	`jnl`	The geometry of integration in text classification RNNs. CoRR Kyle Aitken, Vinay V. Ramasesh, Ankush Garg, Yuan Cao, David Sussillo, Niru Maheswaranathan
2020	J	`jnl`	Using a thousand optimization tasks to learn hyperparameter search strategies. CoRR Luke Metz, Niru Maheswaranathan, Ruoxi Sun, C. Daniel Freeman, Ben Poole, Jascha Sohl-Dickstein
2019	A*	`conf`	From deep learning to mechanistic understanding in neuroscience: the structure of retinal prediction. NeurIPS Hidenori Tanaka, Aran Nayebi, Niru Maheswaranathan, Lane McIntosh, Stephen Baccus, Surya Ganguli
2019	J	`jnl`	From deep learning to mechanistic understanding in neuroscience: the structure of retinal prediction. CoRR Hidenori Tanaka, Aran Nayebi, Niru Maheswaranathan, Lane McIntosh, Stephen A. Baccus, Surya Ganguli
2019	A*	`conf`	Guided evolutionary strategies: augmenting random search with surrogate gradients. ICML Niru Maheswaranathan, Luke Metz, George Tucker, Dami Choi, Jascha Sohl-Dickstein
2019	—	`conf`	Meta-Learning Update Rules for Unsupervised Representation Learning. ICLR Luke Metz, Niru Maheswaranathan, Brian Cheung, Jascha Sohl-Dickstein
2019	A*	`conf`	Reverse engineering recurrent networks for sentiment classification reveals line attractor dynamics. NeurIPS Niru Maheswaranathan, Alex H. Williams, Matthew D. Golub, Surya Ganguli, David Sussillo
2019	J	`jnl`	Reverse engineering recurrent networks for sentiment classification reveals line attractor dynamics. CoRR Niru Maheswaranathan, Alex H. Williams, Matthew D. Golub, Surya Ganguli, David Sussillo
2019	A*	`conf`	Understanding and correcting pathologies in the training of learned optimizers. ICML Luke Metz, Niru Maheswaranathan, Jeremy Nixon, C. Daniel Freeman, Jascha Sohl-Dickstein
2019	A*	`conf`	Universality and individuality in neural dynamics across large populations of recurrent networks. NeurIPS Niru Maheswaranathan, Alex H. Williams, Matthew D. Golub, Surya Ganguli, David Sussillo
2019	J	`jnl`	Universality and individuality in neural dynamics across large populations of recurrent networks. CoRR Niru Maheswaranathan, Alex H. Williams, Matthew D. Golub, Surya Ganguli, David Sussillo
2019	J	`jnl`	Using learned optimizers to make models robust to input noise. CoRR Luke Metz, Niru Maheswaranathan, Jonathon Shlens, Jascha Sohl-Dickstein, Ekin D. Cubuk
2018	J	`jnl`	Guided evolutionary strategies: escaping the curse of dimensionality in random search. CoRR Niru Maheswaranathan, Luke Metz, George Tucker, Jascha Sohl-Dickstein
2018	J	`jnl`	Inferring hidden structure in multilayered neural circuits. PLoS Comput. Biol. Niru Maheswaranathan, David B. Kastner, Stephen A. Baccus, Surya Ganguli
2018	J	`jnl`	Learned optimizers that outperform SGD on wall-clock and test loss. CoRR Luke Metz, Niru Maheswaranathan, Jeremy Nixon, C. Daniel Freeman, Jascha Sohl-Dickstein
2018	J	`jnl`	Learning Unsupervised Learning Rules. CoRR Luke Metz, Niru Maheswaranathan, Brian Cheung, Jascha Sohl-Dickstein
2018	—	`conf`	Learning to Learn Without Labels. ICLR (Workshop) Luke Metz, Niru Maheswaranathan, Brian Cheung, Jascha Sohl-Dickstein
2018	—	`conf`	Recurrent Segmentation for Variable Computational Budgets. CVPR Workshops Lane McIntosh, Niru Maheswaranathan, David Sussillo, Jonathon Shlens
2017	A*	`conf`	Learned Optimizers that Scale and Generalize. ICML Olga Wichrowska, Niru Maheswaranathan, Matthew W. Hoffman, Sergio Gomez Colmenarejo, Misha Denil, Nando de Freitas, Jascha Sohl-Dickstein
2017	J	`jnl`	Learned Optimizers that Scale and Generalize. CoRR Olga Wichrowska, Niru Maheswaranathan, Matthew W. Hoffman, Sergio Gomez Colmenarejo, Misha Denil, Nando de Freitas, Jascha Sohl-Dickstein
2017	J	`jnl`	Pyret: A Python package for analysis of neurophysiology data. J. Open Source Softw. Benjamin Naecker, Niru Maheswaranathan, Surya Ganguli, Stephen Baccus
2017	J	`jnl`	Recurrent Segmentation for Variable Computational Budgets. CoRR Lane McIntosh, David Sussillo, Niru Maheswaranathan, Jonathon Shlens
2016	—	`conf`	Deep Learning Models of the Retinal Response to Natural Scenes. NIPS Lane McIntosh, Niru Maheswaranathan, Aran Nayebi, Surya Ganguli, Stephen Baccus
2015	A*	`conf`	Deep Unsupervised Learning using Nonequilibrium Thermodynamics. ICML Jascha Sohl-Dickstein, Eric A. Weiss, Niru Maheswaranathan, Surya Ganguli
2015	J	`jnl`	Deep Unsupervised Learning using Nonequilibrium Thermodynamics. CoRR Jascha Sohl-Dickstein, Eric A. Weiss, Niru Maheswaranathan, Surya Ganguli
2012	J	`jnl`	Emergent bursting and synchrony in computer simulations of neuronal cultures. Frontiers Comput. Neurosci. Niru Maheswaranathan, Silvia Ferrari, Antonius M. J. VanDongen, Craig Henriquez