Alexander A. Alemi

48 papers A* 10A 1Journal 32Unranked 5

Year	Rank	Type	Title / Venue / Authors
2024	J	`jnl`	Beyond Human Data: Scaling Self-Training for Problem-Solving with Language Models. Trans. Mach. Learn. Res. Avi Singh, John D. Co-Reyes, Rishabh Agarwal, Ankesh Anand, Piyush Patil, Xavier Garcia, Peter J. Liu, James Harrison, Jaehoon Lee, Kelvin Xu, Aaron T. Parisi, Abhishek Kumar, Alexander A. Alemi, Alex Rizkowsky, Azade Nova, Ben Adlam, Bernd Bohnet, Gamaleldin Fathy Elsayed, Hanie Sedghi, Igor Mordatch, Isabelle Simpson, Izzeddin Gur, Jasper Snoek, Jeffrey Pennington, Jiri Hron, Kathleen Kenealy, Kevin Swersky, Kshiteej Mahajan, Laura Culp, Lechao Xiao, Maxwell L. Bileschi, Noah Constant, Roman Novak, Rosanne Liu, Tris Warkentin, Yundi Qian, Yamini Bansal, Ethan Dyer, Behnam Neyshabur, Jascha Sohl-Dickstein, Noah Fiedel
2024	A*	`conf`	Scaling Exponents Across Parameterizations and Optimizers. ICML Katie E. Everett, Lechao Xiao, Mitchell Wortsman, Alexander A. Alemi, Roman Novak, Peter J. Liu, Izzeddin Gur, Jascha Sohl-Dickstein, Leslie Pack Kaelbling, Jaehoon Lee, Jeffrey Pennington
2024	J	`jnl`	Scaling Exponents Across Parameterizations and Optimizers. CoRR Katie Everett, Lechao Xiao, Mitchell Wortsman, Alexander A. Alemi, Roman Novak, Peter J. Liu, Izzeddin Gur, Jascha Sohl-Dickstein, Leslie Pack Kaelbling, Jaehoon Lee, Jeffrey Pennington
2024	A*	`conf`	Small-scale proxies for large-scale Transformer training instabilities. ICLR Mitchell Wortsman, Peter J. Liu, Lechao Xiao, Katie E. Everett, Alexander A. Alemi, Ben Adlam, John D. Co-Reyes, Izzeddin Gur, Abhishek Kumar, Roman Novak, Jeffrey Pennington, Jascha Sohl-Dickstein, Kelvin Xu, Jaehoon Lee, Justin Gilmer, Simon Kornblith
2024	J	`jnl`	Training LLMs over Neurally Compressed Text. Trans. Mach. Learn. Res. Brian Lester, Jaehoon Lee, Alexander A. Alemi, Jeffrey Pennington, Adam Roberts, Jascha Sohl-Dickstein, Noah Constant
2023	J	`jnl`	Speed Limits for Deep Learning. CoRR Inbar Seroussi, Alexander A. Alemi, Moritz Helias, Zohar Ringel
2023	J	`jnl`	Variational Prediction. CoRR Alexander A. Alemi, Ben Poole
2023	A*	`conf`	Weighted Ensemble Self-Supervised Learning. ICLR Yangjun Ruan, Saurabh Singh, Warren Richard Morningstar, Alexander A. Alemi, Sergey Ioffe, Ian Fischer, Joshua V. Dillon
2022	J	`jnl`	Bayesian Imitation Learning for End-to-End Mobile Manipulation. CoRR Yuqing Du, Daniel Ho, Alexander A. Alemi, Eric Jang, Mohi Khansari
2022	J	`jnl`	Weighted Ensemble Self-Supervised Learning. CoRR Yangjun Ruan, Saurabh Singh, Warren R. Morningstar, Alexander A. Alemi, Sergey Ioffe, Ian Fischer, Joshua V. Dillon
2021	J	`jnl`	A Closer Look at the Adversarial Robustness of Information Bottleneck Models. CoRR Iryna Korshunova, David Stutz, Alexander A. Alemi, Olivia Wiles, Sven Gowal
2021	A	`conf`	Density of States Estimation for Out of Distribution Detection. AISTATS Warren R. Morningstar, Cusuh Ham, Andrew G. Gallagher, Balaji Lakshminarayanan, Alexander A. Alemi, Joshua V. Dillon
2021	A*	`conf`	Does Knowledge Distillation Really Work? NeurIPS Samuel Stanton, Pavel Izmailov, Polina Kirichenko, Alexander A. Alemi, Andrew Gordon Wilson
2021	J	`jnl`	Does Knowledge Distillation Really Work? CoRR Samuel Stanton, Pavel Izmailov, Polina Kirichenko, Alexander A. Alemi, Andrew Gordon Wilson
2020	J	`jnl`	CEB Improves Model Robustness. CoRR Ian Fischer, Alexander A. Alemi
2020	J	`jnl`	CEB Improves Model Robustness. Entropy Ian Fischer, Alexander A. Alemi
2020	J	`jnl`	Density of States Estimation for Out-of-Distribution Detection. CoRR Warren R. Morningstar, Cusuh Ham, Andrew G. Gallagher, Balaji Lakshminarayanan, Alexander A. Alemi, Joshua V. Dillon
2020	A*	`conf`	Neural Tangents: Fast and Easy Infinite Neural Networks in Python. ICLR Roman Novak, Lechao Xiao, Jiri Hron, Jaehoon Lee, Alexander A. Alemi, Jascha Sohl-Dickstein, Samuel S. Schoenholz
2020	J	`jnl`	PAC CoRR Warren R. Morningstar, Alexander A. Alemi, Joshua V. Dillon
2020	J	`jnl`	VIB is Half Bayes. CoRR Alexander A. Alemi, Warren R. Morningstar, Ben Poole, Ian Fischer, Joshua V. Dillon
2019	—	`conf`	Information in Infinite Ensembles of Infinitely-Wide Neural Networks. AABI Ravid Shwartz-Ziv, Alexander A. Alemi
2019	J	`jnl`	Information in Infinite Ensembles of Infinitely-Wide Neural Networks. CoRR Ravid Shwartz-Ziv, Alexander A. Alemi
2019	J	`jnl`	Neural Tangents: Fast and Easy Infinite Neural Networks in Python. CoRR Roman Novak, Lechao Xiao, Jiri Hron, Jaehoon Lee, Alexander A. Alemi, Jascha Sohl-Dickstein, Samuel S. Schoenholz
2019	J	`jnl`	On Predictive Information Sub-optimality of RNNs. CoRR Zhe Dong, Deniz Oktay, Ben Poole, Alexander A. Alemi
2019	A*	`conf`	On Variational Bounds of Mutual Information. ICML Ben Poole, Sherjil Ozair, Aäron van den Oord, Alexander A. Alemi, George Tucker
2019	J	`jnl`	On Variational Bounds of Mutual Information. CoRR Ben Poole, Sherjil Ozair, Aäron van den Oord, Alexander A. Alemi, George Tucker
2019	J	`jnl`	On the Use of ArXiv as a Dataset. CoRR Colin B. Clement, Matthew Bierbaum, Kevin P. O'Keeffe, Alexander A. Alemi
2019	J	`jnl`	Thermodynamic Computing. CoRR Tom Conte, Erik DeBenedictis, Natesh Ganesh, Todd Hylton, John Paul Strachan, R. Stanley Williams, Alexander A. Alemi, Lee Altenberg, Gavin E. Crooks, James P. Crutchfield, Lídia del Rio, Josh Deutsch, Michael Robert DeWeese, Khari Douglas, Massimiliano Esposito, Michael P. Frank, Robert Fry, Peter Harsha, Mark D. Hill, Christopher T. Kello, Jeff Krichmar, Suhas Kumar, Shih-Chii Liu, Seth Lloyd, Matteo Marsili, Ilya Nemenman, Alex Nugent, Norman H. Packard, Dana Randall, Peter Sadowski, Narayana Santhanam, Robert Shaw, Adam Z. Stieg, Elan Stopnitzky, Christof Teuscher, Chris Watkins, David H. Wolpert, J. Joshua Yang, Yan Yufik
2019	—	`conf`	Variational Predictive Information Bottleneck. AABI Alexander A. Alemi
2019	J	`jnl`	Variational Predictive Information Bottleneck. CoRR Alexander A. Alemi
2018	A*	`conf`	Fixing a Broken ELBO. ICML Alexander A. Alemi, Ben Poole, Ian Fischer, Joshua V. Dillon, Rif A. Saurous, Kevin Murphy
2018	—	`conf`	GILBO: One Metric to Measure Them All. ICLR (Workshop) Alexander A. Alemi, Ian Fischer
2018	A*	`conf`	GILBO: One Metric to Measure Them All. NeurIPS Alexander A. Alemi, Ian Fischer
2018	J	`jnl`	GILBO: One Metric to Measure Them All. CoRR Alexander A. Alemi, Ian Fischer
2018	J	`jnl`	TherML: Thermodynamics of Machine Learning. CoRR Alexander A. Alemi, Ian Fischer
2018	J	`jnl`	Uncertainty in the Variational Information Bottleneck. CoRR Alexander A. Alemi, Ian Fischer, Joshua V. Dillon
2018	A*	`conf`	Watch Your Step: Learning Node Embeddings via Graph Attention. NeurIPS Sami Abu-El-Haija, Bryan Perozzi, Rami Al-Rfou, Alexander A. Alemi
2018	J	`jnl`	β-VAEs can retain label information even at high compression. CoRR Emily Fertig, Aryan Arbabi, Alexander A. Alemi
2017	J	`jnl`	An Information-Theoretic Analysis of Deep Latent-Variable Models. CoRR Alexander A. Alemi, Ben Poole, Ian Fischer, Joshua V. Dillon, Rif A. Saurous, Kevin Murphy
2017	—	`conf`	Deep Variational Information Bottleneck. ICLR (Poster) Alexander A. Alemi, Ian Fischer, Joshua V. Dillon, Kevin Murphy
2017	A*	`conf`	Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning. AAAI Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke, Alexander A. Alemi
2017	J	`jnl`	Jeffrey's prior sampling of deep sigmoidal networks. CoRR Lorien X. Hayden, Alexander A. Alemi, Paul H. Ginsparg, James P. Sethna
2016	J	`jnl`	Deep Variational Information Bottleneck. CoRR Alexander A. Alemi, Ian Fischer, Joshua V. Dillon, Kevin Murphy
2016	—	`conf`	DeepMath - Deep Sequence Models for Premise Selection. NIPS Geoffrey Irving, Christian Szegedy, Alexander A. Alemi, Niklas Eén, François Chollet, Josef Urban
2016	J	`jnl`	DeepMath - Deep Sequence Models for Premise Selection. CoRR Alexander A. Alemi, François Chollet, Geoffrey Irving, Christian Szegedy, Josef Urban
2016	J	`jnl`	Improved generator objectives for GANs. CoRR Ben Poole, Alexander A. Alemi, Jascha Sohl-Dickstein, Anelia Angelova
2015	J	`jnl`	Clustering via Content-Augmented Stochastic Blockmodels. CoRR J. Massey Cashore, Xiaoting Zhao, Alexander A. Alemi, Yujia Liu, Peter I. Frazier
2015	J	`jnl`	Text Segmentation based on Semantic Word Embeddings. CoRR Alexander A. Alemi, Paul Ginsparg