Skip to yearly menu bar Skip to main content


(15 events)   Timezone:  
Show all
Toggle Poster Visibility
Spotlight
Wed Jul 20 07:30 AM -- 07:35 AM (PDT) @ Ballroom 1 & 2
Towards understanding how momentum improves generalization in deep learning
In Deep Learning
Samy Jelassi · Yuanzhi Li
Spotlight
Wed Jul 20 07:35 AM -- 07:40 AM (PDT) @ Ballroom 1 & 2
What Can Linear Interpolation of Neural Network Loss Landscapes Tell Us?
In Deep Learning
Tiffany Vlaar · Jonathan Frankle
Spotlight
Wed Jul 20 07:40 AM -- 07:45 AM (PDT) @ Ballroom 1 & 2
Deep equilibrium networks are sensitive to initialization statistics
In Deep Learning
Atish Agarwala · Samuel Schoenholz
Spotlight
Wed Jul 20 07:45 AM -- 07:50 AM (PDT) @ Ballroom 1 & 2
Scaling-up Diverse Orthogonal Convolutional Networks by a Paraunitary Framework
In Deep Learning
Jiahao Su · Wonmin Byeon · Furong Huang
Spotlight
Wed Jul 20 07:50 AM -- 07:55 AM (PDT) @ Ballroom 1 & 2
Stability Based Generalization Bounds for Exponential Family Langevin Dynamics
In Deep Learning
Arindam Banerjee · Tiancong Chen · Xinyan Li · Yingxue Zhou
Spotlight
Wed Jul 20 07:55 AM -- 08:00 AM (PDT) @ Ballroom 1 & 2
Local Augmentation for Graph Neural Networks
In Deep Learning
Songtao Liu · Rex (Zhitao) Ying · Hanze Dong · Lanqing Li · Tingyang Xu · Yu Rong · Peilin Zhao · Junzhou Huang · Dinghao Wu
Spotlight
Wed Jul 20 08:00 AM -- 08:05 AM (PDT) @ Ballroom 1 & 2
On Non-local Convergence Analysis of Deep Linear Networks
In Deep Learning
Kun Chen · Dachao Lin · Zhihua Zhang
Oral
Wed Jul 20 08:05 AM -- 08:25 AM (PDT) @ Ballroom 1 & 2
Adaptive Inertia: Disentangling the Effects of Adaptive Learning Rate and Momentum
In Deep Learning
Zeke Xie · Xinrui Wang · Huishuai Zhang · Issei Sato · Masashi Sugiyama
Spotlight
Wed Jul 20 08:25 AM -- 08:30 AM (PDT) @ Ballroom 1 & 2
Diversified Adversarial Attacks based on Conjugate Gradient Method
In Deep Learning
Keiichiro Yamamura · Haruki Sato · Nariaki Tateiwa · Nozomi Hata · Toru Mitsutake · Issa Oe · Hiroki Ishikura · Katsuki Fujisawa
Spotlight
Wed Jul 20 08:30 AM -- 08:35 AM (PDT) @ Ballroom 1 & 2
On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features
In Deep Learning
Jinxin Zhou · Xiao Li · Tianyu Ding · Chong You · Qing Qu · Zhihui Zhu
Spotlight
Wed Jul 20 08:35 AM -- 08:40 AM (PDT) @ Ballroom 1 & 2
On the Equivalence Between Temporal and Static Equivariant Graph Representations
In Deep Learning
Jianfei Gao · Bruno Ribeiro
Spotlight
Wed Jul 20 08:40 AM -- 08:45 AM (PDT) @ Ballroom 1 & 2
Robust Training under Label Noise by Over-parameterization
In Deep Learning
Sheng Liu · Zhihui Zhu · Qing Qu · Chong You
Spotlight
Wed Jul 20 08:45 AM -- 08:50 AM (PDT) @ Ballroom 1 & 2
Implicit Bias of the Step Size in Linear Diagonal Neural Networks
In Deep Learning
Mor Shpigel Nacson · Kavya Ravichandran · Nati Srebro · Daniel Soudry
Spotlight
Wed Jul 20 08:50 AM -- 08:55 AM (PDT) @ Ballroom 1 & 2
Extended Unconstrained Features Model for Exploring Deep Neural Collapse
In Deep Learning
Tom Tirer · Joan Bruna
Spotlight
Wed Jul 20 08:55 AM -- 09:00 AM (PDT) @ Ballroom 1 & 2
Score-Guided Intermediate Level Optimization: Fast Langevin Mixing for Inverse Problems
In Deep Learning
Giannis Daras · Yuval Dagan · Alexandros Dimakis · Constantinos Daskalakis