Deep learning interpretation: Flip points and homotopy methods

Roozbeh Yousefzadeh, Dianne P. O’Leary; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:1-26

[abs][Download PDF]

Rademacher complexity and spin glasses: A link between the replica and statistical theories of learning

Alia Abbaras, Benjamin Aubin, Florent Krzakala, Lenka Zdeborová; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:27-54

[abs][Download PDF]

Exact asymptotics for phase retrieval and compressed sensing with random generative priors

Benjamin Aubin, Bruno Loureiro, Antoine Baker, Florent Krzakala, Lenka Zdeborová; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:55-73

[abs][Download PDF]

SchrödingerRNN: Generative modeling of raw audio as a continuously observed quantum state

Beñat Mencia Uranga, Austen Lamacraft; Proceedings of the First Mathematical and Scientific Machine Learning Conference, PMLR 107:74-106

[abs][Download PDF]

On the stable recovery of deep structured linear networks under sparsity constraints

François Malgouyres; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:107-127

[abs][Download PDF]

Neural network integral representations with the ReLU activation function

Armenak Petrosyan, Anton Dereventsov, Clayton G. Webster; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:128-143

[abs][Download PDF]

A type of generalization error induced by initialization in deep neural networks

Yaoyu Zhang, Zhi-Qin John Xu, Tao Luo, Zheng Ma; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:144-164

[abs][Download PDF]

Non-Gaussian processes and neural networks at finite widths

Sho Yaida; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:165-192

[abs][Download PDF]

SelectNet: Learning to Sample from the Wild for Imbalanced Data Training

Yunru Liu, Tingran Gao, Haizhao Yang; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:193-206

[abs][Download PDF]

Calibrating Multivariate Lévy Processes with Neural Networks

Kailai Xu, Eric Darve; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:207-220

[abs][Download PDF]

Deep Fictitious Play for Finding Markovian Nash Equilibrium in Multi-Agent Games

Jiequn Han, Ruimeng Hu; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:221-245

[abs][Download PDF]

Borrowing From the Future: An Attempt to Address Double Sampling

Yuhua Zhu, Lexing Ying; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:246-268

[abs][Download PDF]

Deep Domain Decomposition Method: Elliptic Problems

Wuyang Li, Xueshuang Xiang, Yingxiang Xu; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:269-286

[abs][Download PDF]

Landscape Complexity for the Empirical Risk of Generalized Linear Models

Antoine Maillard, Gérard Ben Arous, Giulio Biroli; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:287-327

[abs][Download PDF]

DP-LSSGD: A Stochastic Optimization Method to Lift the Utility in Privacy-Preserving ERM

Bao Wang, Quanquan Gu, March Boedihardjo, Lingxiao Wang, Farzin Barekat, Stanley J. Osher; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:328-351

[abs][Download PDF]

NeuPDE: Neural Network Based Ordinary and Partial Differential Equations for Modeling Time-Dependent Data

Yifan Sun, Linan Zhang, Hayden Schaeffer; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:352-372

[abs][Download PDF]

The Slow Deterioration of the Generalization Error of the Random Feature Model

Chao Ma, Lei Wu, Weinan E; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:373-389

[abs][Download PDF]

Large deviations for the perceptron model and consequences for active learning

Hugo Cui, Luca Saglietti, Lenka Zdeborova; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:390-430

[abs][Download PDF]

Butterfly-Net2: Simplified Butterfly-Net and Fourier Transform Initialization

Zhongshu Xu, Yingzhou Li, Xiuyuan Cheng; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:431-450

[abs][Download PDF]

Deep learning Markov and Koopman models with physical constraints

Andreas Mardt, Luca Pasquali, Frank Noé, Hao Wu; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:451-475

[abs][Download PDF]

Gating creates slow modes and controls phase-space complexity in GRUs and LSTMs

Tankut Can, Kamesh Krishnamurthy, David J. Schwab; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:476-511

[abs][Download PDF]

Robust Training and Initialization of Deep Neural Networks: An Adaptive Basis Viewpoint

Eric C. Cyr, Mamikon A. Gulian, Ravi G. Patel, Mauro Perego, Nathaniel A. Trask; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:512-536

[abs][Download PDF]

New Potential-Based Bounds for the Geometric-Stopping Version of Prediction with Expert Advice

Vladimir A. Kobzar, Robert V. Kohn, Zhilei Wang; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:537-554

[abs][Download PDF]

Data-driven Compact Models for Circuit Design and Analysis

K. Aadithya, P. Kuberry, B. Paskaleva, P. Bochev, K. Leeson, A. Mar, T. Mei, E. Keiter; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:555-569

[abs][Download PDF]

Geometric Wavelet Scattering Networks on Compact Riemannian Manifolds

Michael Perlmutter, Feng Gao, Guy Wolf, Matthew Hirn; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:570-604

[abs][Download PDF]

Policy Gradient based Quantum Approximate Optimization Algorithm

Jiahao Yao, Marin Bukov, Lin Lin; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:605-634

[abs][Download PDF]

Quantum Ground States from Reinforcement Learning

Ariel Barr, Willem Gispen, Austen Lamacraft; Proceedings of The First Mathematical and Scientific Machine Learning Conference, PMLR 107:635-653

[abs][Download PDF]