Timezone: »
Compositionality is a basic structural feature of both biological and artificial neural networks. Learning compositional functions via gradient descent incurs well known problems like vanishing and exploding gradients, making careful learning rate tuning essential for real-world applications. This paper proves that multiplicative weight updates satisfy a descent lemma tailored to compositional functions. Based on this lemma, we derive Madam---a multiplicative version of the Adam optimiser---and show that it can train state of the art neural network architectures without learning rate tuning. We further show that Madam is easily adapted to train natively compressed neural networks by representing their weights in a logarithmic number system. We conclude by drawing connections between multiplicative weight updates and recent findings about synapses in biology.
Author Information
Jeremy Bernstein (Caltech)
Jiawei Zhao (Caltech)
Markus Meister (Caltech)
Ming-Yu Liu (NVIDIA)
Anima Anandkumar (NVIDIA / Caltech)
Anima Anandkumar is a Bren professor at Caltech CMS department and a director of machine learning research at NVIDIA. Her research spans both theoretical and practical aspects of large-scale machine learning. In particular, she has spearheaded research in tensor-algebraic methods, non-convex optimization, probabilistic models and deep learning. Anima is the recipient of several awards and honors such as the Bren named chair professorship at Caltech, Alfred. P. Sloan Fellowship, Young investigator awards from the Air Force and Army research offices, Faculty fellowships from Microsoft, Google and Adobe, and several best paper awards. Anima received her B.Tech in Electrical Engineering from IIT Madras in 2004 and her PhD from Cornell University in 2009. She was a postdoctoral researcher at MIT from 2009 to 2010, a visiting researcher at Microsoft Research New England in 2012 and 2014, an assistant professor at U.C. Irvine between 2010 and 2016, an associate professor at U.C. Irvine between 2016 and 2017 and a principal scientist at Amazon Web Services between 2016 and 2018.
Yisong Yue (Caltech)
More from the Same Authors
-
2020 Workshop: Learning Meets Combinatorial Algorithms »
Marin Vlastelica · Jialin Song · Aaron Ferber · Brandon Amos · Georg Martius · Bistra Dilkina · Yisong Yue -
2020 Workshop: Machine Learning and the Physical Sciences »
Anima Anandkumar · Kyle Cranmer · Shirley Ho · Mr. Prabhat · Lenka Zdeborová · Atilim Gunes Baydin · Juan Carrasquilla · Adji Bousso Dieng · Karthik Kashinath · Gilles Louppe · Brian Nord · Michela Paganini · Savannah Thais -
2020 Poster: Online Optimization with Memory and Competitive Control »
Guanya Shi · Yiheng Lin · Soon-Jo Chung · Yisong Yue · Adam Wierman -
2020 Poster: A General Large Neighborhood Search Framework for Solving Integer Linear Programs »
Jialin Song · ravi lanka · Yisong Yue · Bistra Dilkina -
2020 Poster: Learning Differentiable Programs with Admissible Neural Heuristics »
Ameesh Shah · Eric Zhan · Jennifer Sun · Abhinav Verma · Yisong Yue · Swarat Chaudhuri -
2020 Poster: Neural Networks with Recurrent Generative Feedback »
Yujia Huang · James Gornet · Sihui Dai · Zhiding Yu · Tan Nguyen · Doris Tsao · Anima Anandkumar -
2020 Poster: Causal Discovery in Physical Systems from Videos »
Yunzhu Li · Antonio Torralba · Anima Anandkumar · Dieter Fox · Animesh Garg -
2020 Poster: Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning »
Weili Nie · Zhiding Yu · Lei Mao · Ankit Patel · Yuke Zhu · Anima Anandkumar -
2020 Spotlight: Bongard-LOGO: A New Benchmark for Human-Level Concept Learning and Reasoning »
Weili Nie · Zhiding Yu · Lei Mao · Ankit Patel · Yuke Zhu · Anima Anandkumar -
2020 Poster: Multipole Graph Neural Operator for Parametric Partial Differential Equations »
Zongyi Li · Nikola Kovachki · Kamyar Azizzadenesheli · Burigede Liu · Andrew Stuart · Kaushik Bhattacharya · Anima Anandkumar -
2020 Poster: Convolutional Tensor-Train LSTM for Spatio-Temporal Learning »
Jiahao Su · Wonmin Byeon · Jean Kossaifi · Furong Huang · Jan Kautz · Anima Anandkumar -
2020 Poster: On the distance between two neural networks and the stability of learning »
Jeremy Bernstein · Arash Vahdat · Yisong Yue · Ming-Yu Liu -
2020 Poster: The Power of Predictions in Online Control »
Chenkai Yu · Guanya Shi · Soon-Jo Chung · Yisong Yue · Adam Wierman -
2020 Poster: Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems »
Sahin Lale · Kamyar Azizzadenesheli · Babak Hassibi · Anima Anandkumar -
2019 Workshop: Machine Learning and the Physical Sciences »
Atilim Gunes Baydin · Juan Carrasquilla · Shirley Ho · Karthik Kashinath · Michela Paganini · Savannah Thais · Anima Anandkumar · Kyle Cranmer · Roger Melko · Mr. Prabhat · Frank Wood -
2019 Workshop: Safety and Robustness in Decision-making »
Mohammad Ghavamzadeh · Shie Mannor · Yisong Yue · Marek Petrik · Yinlam Chow -
2019 Poster: Competitive Gradient Descent »
Florian Schaefer · Anima Anandkumar -
2019 Poster: Imitation-Projected Programmatic Reinforcement Learning »
Abhinav Verma · Hoang Le · Yisong Yue · Swarat Chaudhuri -
2019 Poster: NAOMI: Non-Autoregressive Multiresolution Sequence Imputation »
Yukai Liu · Rose Yu · Stephan Zheng · Eric Zhan · Yisong Yue -
2019 Poster: Teaching Multiple Concepts to a Forgetful Learner »
Anette Hunziker · Yuxin Chen · Oisin Mac Aodha · Manuel Gomez Rodriguez · Andreas Krause · Pietro Perona · Yisong Yue · Adish Singla -
2019 Poster: Landmark Ordinal Embedding »
Nikhil Ghosh · Yuxin Chen · Yisong Yue -
2018 Workshop: Integration of Deep Learning Theories »
Richard Baraniuk · Anima Anandkumar · Stephane Mallat · Ankit Patel · nhật Hồ -
2018 Poster: Understanding the Role of Adaptivity in Machine Teaching: The Case of Version Space Learners »
Yuxin Chen · Adish Singla · Oisin Mac Aodha · Pietro Perona · Yisong Yue -
2018 Poster: A General Method for Amortizing Variational Filtering »
Joseph Marino · Milan Cvitkovic · Yisong Yue -
2016 Workshop: Learning with Tensors: Why Now and How? »
Anima Anandkumar · Rong Ge · Yan Liu · Maximilian Nickel · Qi (Rose) Yu -
2016 Workshop: Nonconvex Optimization for Machine Learning: Theory and Practice »
Hossein Mobahi · Anima Anandkumar · Percy Liang · Stefanie Jegelka · Anna Choromanska -
2016 Poster: Generating Long-term Trajectories Using Deep Hierarchical Networks »
Stephan Zheng · Yisong Yue · Patrick Lucey -
2016 Poster: Online and Differentially-Private Tensor Decomposition »
Yining Wang · Anima Anandkumar -
2015 Workshop: Non-convex Optimization for Machine Learning: Theory and Practice »
Anima Anandkumar · Niranjan Uma Naresh · Kamalika Chaudhuri · Percy Liang · Sewoong Oh -
2015 Poster: Smooth Interactive Submodular Set Cover »
Bryan He · Yisong Yue -
2015 Poster: Fast and Guaranteed Tensor Decomposition via Sketching »
Yining Wang · Hsiao-Yu Tung · Alexander Smola · Anima Anandkumar -
2015 Spotlight: Fast and Guaranteed Tensor Decomposition via Sketching »
Yining Wang · Hsiao-Yu Tung · Alexander Smola · Anima Anandkumar -
2015 Demonstration: Data-Driven Speech Animation »
Yisong Yue · Iain Matthews -
2014 Poster: Multi-Step Stochastic ADMM in High Dimensions: Applications to Sparse Optimization and Matrix Decomposition »
Hanie Sedghi · Anima Anandkumar · Edmond A Jonckheere -
2014 Poster: Non-convex Robust PCA »
Praneeth Netrapalli · Niranjan Uma Naresh · Sujay Sanghavi · Animashree Anandkumar · Prateek Jain -
2014 Spotlight: Non-convex Robust PCA »
Praneeth Netrapalli · Niranjan Uma Naresh · Sujay Sanghavi · Animashree Anandkumar · Prateek Jain -
2013 Workshop: Topic Models: Computation, Application, and Evaluation »
David Mimno · Amr Ahmed · Jordan Boyd-Graber · Ankur Moitra · Hanna Wallach · Alexander Smola · David Blei · Anima Anandkumar -
2013 Poster: When are Overcomplete Topic Models Identifiable? Uniqueness of Tensor Tucker Decompositions with Structured Sparsity »
Anima Anandkumar · Daniel Hsu · Majid Janzamin · Sham M Kakade -
2012 Poster: Learning Mixtures of Tree Graphical Models »
Anima Anandkumar · Daniel Hsu · Furong Huang · Sham M Kakade -
2012 Poster: A Spectral Algorithm for Latent Dirichlet Allocation »
Anima Anandkumar · Dean P Foster · Daniel Hsu · Sham M Kakade · Yi-Kai Liu -
2012 Spotlight: A Spectral Algorithm for Latent Dirichlet Allocation »
Anima Anandkumar · Dean P Foster · Daniel Hsu · Sham M Kakade · Yi-Kai Liu -
2012 Poster: Latent Graphical Model Selection: Efficient Methods for Locally Tree-like Graphs »
Anima Anandkumar · Ragupathyraj Valluvan -
2011 Poster: High-Dimensional Graphical Model Selection: Tractable Graph Families and Necessary Conditions »
Animashree Anandkumar · Vincent Tan · Alan S Willsky -
2011 Oral: High-Dimensional Graphical Model Selection: Tractable Graph Families and Necessary Conditions »
Animashree Anandkumar · Vincent Tan · Alan S Willsky -
2011 Poster: Spectral Methods for Learning Multivariate Latent Tree Structure »
Anima Anandkumar · Kamalika Chaudhuri · Daniel Hsu · Sham M Kakade · Le Song · Tong Zhang