Filter by Keyword:

57 Results

Poster
Tue 7:00 On the Noisy Gradient Descent that Generalizes as SGD
Jingfeng Wu, Wenqing Hu, Haoyi Xiong, Jun Huan, Vladimir Braverman, Zhanxing Zhu
Poster
Tue 7:00 Reverse-engineering deep ReLU networks
David Rolnick, Konrad Kording
Poster
Tue 7:00 Student Specialization in Deep Rectified Networks With Finite Width and Input Dimension
Yuandong Tian
Poster
Tue 7:00 Towards Understanding the Dynamics of the First-Order Adversaries
Zhun Deng, Hangfeng He, Jiaoyang Huang, Weijie Su
Poster
Tue 7:00 Maximum-and-Concatenation Networks
Xingyu Xie, Hao Kong, Jianlong Wu, Wayne Zhang, Guangcan Liu, Zhouchen Lin
Poster
Tue 8:00 Associative Memory in Iterated Overparameterized Sigmoid Autoencoders
Yibo Jiang, Cengiz Pehlevan
Poster
Tue 9:00 Neural Contextual Bandits with UCB-based Exploration
Dongruo Zhou, Lihong Li, Quanquan Gu
Poster
Tue 9:00 Disentangling Trainability and Generalization in Deep Neural Networks
Lechao Xiao, Jeffrey Pennington, Samuel Schoenholz
Poster
Tue 9:00 Low-loss connection of weight vectors: distribution-based approaches
Ivan Anokhin, Dmitry Yarotsky
Poster
Tue 10:00 A Sample Complexity Separation between Non-Convex and Convex Meta-Learning
Nikunj Saunshi, Yi Zhang, Misha Khodak, Sanjeev Arora
Poster
Tue 10:00 On Learning Sets of Symmetric Elements
Haggai Maron, Or Litany, Gal Chechik, Ethan Fetaya
Poster
Tue 10:00 Harmonic Decompositions of Convolutional Networks
Meyer Scetbon, Zaid Harchaoui
Poster
Tue 11:00 Information-Theoretic Local Minima Characterization and Regularization
Zhiwei Jia, Hao Su
Poster
Tue 11:00 When Explanations Lie: Why Many Modified BP Attributions Fail
Leon Sixt, Maximilian Granz, Tim Landgraf
Poster
Tue 11:00 Rethinking Bias-Variance Trade-off for Generalization of Neural Networks
Zitong Yang, Yaodong Yu, Chong You, Jacob Steinhardt, Yi Ma
Poster
Tue 12:00 Constructive Universal High-Dimensional Distribution Generation through Deep ReLU Networks
Dmytro Perekrestenko, Stephan Müller, Helmut Bölcskei
Poster
Tue 13:00 Beyond Signal Propagation: Is Feature Diversity Necessary in Deep Neural Network Initialization?
Yaniv Blumenfeld, Dar Gilboa, Daniel Soudry
Poster
Tue 13:00 Fractional Underdamped Langevin Dynamics: Retargeting SGD with Momentum under Heavy-Tailed Gradient Noise
Umut Simsekli, Lingjiong Zhu, Yee-Whye Teh, Mert Gurbuzbalaban
Poster
Tue 14:00 Random Matrix Theory Proves that Deep Learning Representations of GAN-data Behave as Gaussian Mixtures
Mohamed El Amine Seddik, Cosme Louart, Mohamed Tamaazousti, Romain COUILLET
Poster
Tue 14:00 Infinite attention: NNGP and NTK for deep attention networks
Jiri Hron, Yasaman Bahri, Jascha Sohl-Dickstein, Roman Novak
Poster
Tue 14:00 Compressive sensing with un-trained neural networks: Gradient descent finds a smooth approximation
Reinhard Heckel, Mahdi Soltanolkotabi
Poster
Wed 5:00 Dynamics of Deep Neural Networks and Neural Tangent Hierarchy
Jiaoyang Huang, Horng-Tzer Yau
Poster
Wed 5:00 InstaHide: Instance-hiding Schemes for Private Distributed Learning
Yangsibo Huang, Zhao Song, Kai Li, Sanjeev Arora
Poster
Wed 5:00 Abstraction Mechanisms Predict Generalization in Deep Neural Networks
Alex Gain, Hava Siegelmann
Poster
Wed 5:00 Second-Order Provable Defenses against Adversarial Attacks
Sahil Singla, Soheil Feizi
Poster
Wed 5:00 The Neural Tangent Kernel in High Dimensions: Triple Descent and a Multi-Scale Theory of Generalization
Ben Adlam, Jeffrey Pennington
Poster
Wed 5:00 Eliminating the Invariance on the Loss Landscape of Linear Autoencoders
Reza Oftadeh, Jiayi Shen, Zhangyang Wang, Dylan Shell
Poster
Wed 9:00 Optimization Theory for ReLU Neural Networks Trained with Normalization Layers
Yonatan Dukler, Quanquan Gu, Guido Montufar
Poster
Wed 9:00 A Mean Field Analysis Of Deep ResNet And Beyond: Towards Provably Optimization Via Overparameterization From Depth
Yiping Lu, Chao Ma, Yulong Lu, Jianfeng Lu, Lexing Ying
Poster
Wed 10:00 The Impact of Neural Network Overparameterization on Gradient Confusion and Stochastic Gradient Descent
Karthik Abinav Sankararaman, Soham De, Zheng Xu, W. Ronny Huang, Tom Goldstein
Poster
Wed 11:00 The Implicit and Explicit Regularization Effects of Dropout
Colin Wei, Sham Kakade, Tengyu Ma
Poster
Wed 11:00 On the Number of Linear Regions of Convolutional Neural Networks
Huan Xiong, Lei Huang, Mengyang Yu, Li Liu, Fan Zhu, Ling Shao
Poster
Wed 11:00 Double Trouble in Double Descent: Bias and Variance(s) in the Lazy Regime
Stéphane d'Ascoli, Maria Refinetti, Giulio Biroli, Florent Krzakala
Poster
Wed 11:00 Proving the Lottery Ticket Hypothesis: Pruning is All You Need
Eran Malach, Gilad Yehudai, Shai Shalev-Schwartz, Ohad Shamir
Poster
Wed 12:00 Dissecting Non-Vacuous Generalization Bounds based on the Mean-Field Approximation
Konstantinos Pitas
Poster
Wed 12:00 Unique Properties of Flat Minima in Deep Networks
Rotem Mulayoff, Tomer Michaeli
Poster
Wed 12:00 Training Linear Neural Networks: Non-Local Convergence and Complexity Results
Armin Eftekhari
Poster
Wed 12:00 Convergence Rates of Variational Inference in Sparse Deep Learning
Badr-Eddine Chérief-Abdellatif
Poster
Wed 12:00 Towards a General Theory of Infinite-Width Limits of Neural Classifiers
Eugene Golikov
Poster
Wed 12:00 Optimal Continual Learning has Perfect Memory and is NP-hard
Jeremias Knoblauch, Hisham Husain, Tom Diethe
Poster
Wed 13:00 Attentive Group Equivariant Convolutional Networks
David Romero, Erik Bekkers, Jakub Tomczak, Mark Hoogendoorn
Poster
Wed 13:00 Generalisation error in learning with random features and the hidden manifold model
Federica Gerace, Bruno Loureiro, Florent Krzakala, Marc Mezard, Lenka Zdeborova
Poster
Thu 6:00 Spectrum Dependent Learning Curves in Kernel Regression and Wide Neural Networks
Blake Bordelon, Abdul Canatar, Cengiz Pehlevan
Poster
Thu 6:00 Does label smoothing mitigate label noise?
Michal Lukasik, Srinadh Bhojanapalli, Aditya Menon, Sanjiv Kumar
Poster
Thu 6:00 Do GANs always have Nash equilibria?
Farzan Farnia, Asuman Ozdaglar
Poster
Thu 6:00 Low-Rank Bottleneck in Multi-head Attention Models
Srinadh Bhojanapalli, Chulhee (Charlie) Yun, Ankit Singh Rawat, Sashank Jakkam Reddi, Sanjiv Kumar
Poster
Thu 6:00 Universal Equivariant Multilayer Perceptrons
Siamak Ravanbakhsh
Poster
Thu 7:00 Lorentz Group Equivariant Neural Network for Particle Physics
Alexander Bogatskiy, Brandon Anderson, Jan T Offermann, Marwah Roussi, David Miller, Risi Kondor
Poster
Thu 7:00 Better depth-width trade-offs for neural networks through the lens of dynamical systems
Vaggos Chatziafratis, Sai Ganesh Nagarajan, Ioannis Panageas
Poster
Thu 7:00 Deep Molecular Programming: A Natural Implementation of Binary-Weight ReLU Neural Networks
Marko Vasic, Cameron Chalk, Sarfraz Khurshid, David Soloveichik
Poster
Thu 8:00 SGD Learns One-Layer Networks in WGANs
Qi Lei, Jason Lee, Alex Dimakis, Constantinos Daskalakis
Poster
Thu 8:00 Generalization and Representational Limits of Graph Neural Networks
Vikas K Garg, Stefanie Jegelka, Tommi Jaakkola
Poster
Thu 9:00 Implicit competitive regularization in GANs
Florian Schaefer, Hongkai Zheng, Anima Anandkumar
Poster
Thu 12:00 Topologically Densified Distributions
Christoph Hofer, Florian Graf, Marc Niethammer, Roland Kwitt
Poster
Thu 12:00 Landscape Connectivity and Dropout Stability of SGD Solutions for Over-parameterized Neural Networks
Alexander Shevchenko, Marco Mondelli
Poster
Thu 12:00 Frequency Bias in Neural Networks for Input of Non-Uniform Density
Ronen Basri, Meirav Galun, Amnon Geifman, David Jacobs, Yoni Kasten, Shira Kritchman
Poster
Thu 15:00 Curse of Dimensionality on Randomized Smoothing for Certifiable Robustness
Aounon Kumar, Alexander Levine, Tom Goldstein, Soheil Feizi