arXivDaily arXiv每日学术速递 周一至周五更新

期刊&会议

International Conference on Learning Representations · 会议 · Machine Learning

共收录 9459
1911.01117 2021-06-14 quant-ph cs.ET

Quantum Algorithms for Deep Convolutional Neural Networks

Iordanis Kerenidis, Jonas Landman, Anupam Prakash

Journal ref International Conference on Learning Representations 2020

详情

展开后加载摘要…

URL PDF HTML 收藏
2106.05469 2021-06-11 cs.CL

Variational Information Bottleneck for Effective Low-Resource Fine-Tuning

Rabeeh Karimi Mahabadi, Yonatan Belinkov, James Henderson

Comments ICLR, 2021

详情

展开后加载摘要…

URL PDF HTML 收藏
2104.03469 2021-06-11 cs.LG

Gi and Pal Scores: Deep Neural Network Generalization Statistics

Yair Schiff, Brian Quanz, Payel Das, Pin-Yu Chen

Comments Accepted to RobustML Workshop at ICLR 2021

详情

展开后加载摘要…

URL PDF HTML 收藏
2106.03851 2021-06-09 cs.SD cs.LG eess.AS

Impact of data-splits on generalization: Identifying COVID-19 from cough and context

Makkunda Sharma, Nikhil Shenoy, Jigar Doshi, Piyush Bagad, Aman Dalmia, Parag Bhamare, Amrita Mahale, Saurabh Rane, Neeraj Agrawal, Rahul Panicker

Comments Published as a workshop paper at ICLR 2021 AI for Public Health Workshop and ICLR 20201 Machine Learning for Preventing and Combating Pandemics Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2106.02985 2021-06-08 cs.LG

Escaping Saddle Points Faster with Stochastic Momentum

Jun-Kun Wang, Chi-Heng Lin, Jacob Abernethy

Comments Accepted at ICLR 2020

详情

展开后加载摘要…

URL PDF HTML 收藏
2101.10318 2021-06-08 cs.LG cs.AI

Multi-Time Attention Networks for Irregularly Sampled Time Series

Satya Narayan Shukla, Benjamin M. Marlin

Comments Accepted at International Conference on Learning Representations (ICLR) 2021

详情

展开后加载摘要…

URL PDF HTML 收藏
2012.00780 2021-06-08 cs.LG cs.AI stat.ML

Refining Deep Generative Models via Discriminator Gradient Flow

Abdul Fatir Ansari, Ming Liang Ang, Harold Soh

Comments ICLR 2021 Camera Ready; Code available at https://github.com/clear-nus/DGflow; Updated Related Work

详情

展开后加载摘要…

URL PDF HTML 收藏
2011.12747 2021-06-08 stat.ML cs.LG physics.chem-ph

Symmetry-Aware Actor-Critic for 3D Molecular Design

Gregor N. C. Simm, Robert Pinsler, Gábor Csányi, José Miguel Hernández-Lobato

Journal ref International Conference on Learning Representations, 2021

详情

展开后加载摘要…

URL PDF HTML 收藏
2006.15646 2021-06-08 cs.LG cs.DM stat.ML

Expressive Power of Invariant and Equivariant Graph Neural Networks

Waïss Azizian, Marc Lelarge

Comments Appears in: Proceedings of the 9th International Conference on Learning Representations, ICLR 2021. 39 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2103.10426 2021-06-07 cs.CV cs.LG

Using latent space regression to analyze and leverage compositionality in GANs

Lucy Chai, Jonas Wulff, Phillip Isola

Comments Update to ICLR 2021 camera ready version

详情

展开后加载摘要…

URL PDF HTML 收藏
2106.01901 2021-06-04 cs.MA

Iterative Empirical Game Solving via Single Policy Best Response

Max Olan Smith, Thomas Anthony, Michael P. Wellman

Journal ref ICLR 2021

详情

展开后加载摘要…

URL PDF HTML 收藏
2106.01603 2021-06-04 cs.CV

CT-Net: Channel Tensorization Network for Video Classification

Kunchang Li, Xianhang Li, Yali Wang, Jun Wang, Yu Qiao

Comments ICLR 2021. Code is available on https://github.com/Andy1621/CT-Net

详情

展开后加载摘要…

URL PDF HTML 收藏
2010.11929 2021-06-04 cs.CV cs.AI cs.LG

An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, Neil Houlsby

Comments Fine-tuning code and pre-trained models are available at https://github.com/google-research/vision_transformer. ICLR camera-ready version with 2 small modifications: 1) Added a discussion of CLS vs GAP classifier in the appendix, 2) Fixed an error in exaFLOPs computation in Figure 5 and Table 6 (relative performance of models is basically not affected)

详情

展开后加载摘要…

URL PDF HTML 收藏
2106.01251 2021-06-03 cs.CL cs.IR

Multilingual Medical Question Answering and Information Retrieval for Rural Health Intelligence Access

Vishal Vinod, Susmit Agrawal, Vipul Gaurav, Pallavi R, Savita Choudhary

Journal ref ICLR 2021 Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2106.00920 2021-06-03 cs.CL cs.AI cs.LG

DialoGraph: Incorporating Interpretable Strategy-Graph Networks into Negotiation Dialogues

Rishabh Joshi, Vidhisha Balachandran, Shikhar Vashishth, Alan Black, Yulia Tsvetkov

Comments Accepted at ICLR 2021; https://openreview.net/forum?id=kDnal_bbb-E

详情

展开后加载摘要…

URL PDF HTML 收藏
2106.00750 2021-06-03 cs.LG stat.ML

Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding

Sana Tonekaboni, Danny Eytan, Anna Goldenberg

Comments Camera-ready at ICLR 2021

详情

展开后加载摘要…

URL PDF HTML 收藏
2012.01696 2021-06-03 cs.LG cs.AI stat.ML

FairBatch: Batch Selection for Model Fairness

Yuji Roh, Kangwook Lee, Steven Euijong Whang, Changho Suh

Comments In Proceedings of the 9th International Conference on Learning Representations (ICLR), 2021

详情

展开后加载摘要…

URL PDF HTML 收藏
2106.00317 2021-06-02 cs.LG

Data-Driven Shadowgraph Simulation of a 3D Object

Anna Willmann, Patrick Stiller, Alexander Debus, Arie Irman, Richard Pausch, Yen-Yu Chang, Michael Bussmann, Nico Hoffmann

Comments 9 pages, 9 figures. Published as a workshop paper at ICLR 2021 SimDL Workshop

详情

展开后加载摘要…

URL PDF HTML 收藏
2101.08687 2021-06-02 cs.LG

Overfitting for Fun and Profit: Instance-Adaptive Data Compression

Ties van Rozendaal, Iris A. M. Huijben, Taco S. Cohen

Comments Accepted at International Conference on Learning Representations 2021

详情

展开后加载摘要…

URL PDF HTML 收藏
2105.14602 2021-06-01 cs.LG cond-mat.dis-nn stat.ML

On the geometry of generalization and memorization in deep neural networks

Cory Stephenson, Suchismita Padhy, Abhinav Ganesh, Yue Hui, Hanlin Tang, SueYeon Chung

Comments ICLR 2021

详情

展开后加载摘要…

URL PDF HTML 收藏
2105.09992 2021-06-01 cs.LG

Don't Do What Doesn't Matter: Intrinsic Motivation with Action Usefulness

Mathieu Seurin, Florian Strub, Philippe Preux, Olivier Pietquin

Comments Accepted at Internationnal Joint Conference on Artificial Intelligence (IJCAI'21) and Self-Supervision for Reinforcement Learning Workshop (SSL-RL @ICLR'21)

详情

展开后加载摘要…

URL PDF HTML 收藏
2101.11665 2021-06-01 stat.ML cs.LG

On Statistical Bias In Active Learning: How and When To Fix It

Sebastian Farquhar, Yarin Gal, Tom Rainforth

Comments Published at ICLR 2021 (Spotlight)

详情

展开后加载摘要…

URL PDF HTML 收藏
2010.01736 2021-06-01 cs.LG cs.AI

Geometry-aware Instance-reweighted Adversarial Training

Jingfeng Zhang, Jianing Zhu, Gang Niu, Bo Han, Masashi Sugiyama, Mohan Kankanhalli

Comments ICLR 2021, Oral, Code <https://github.com/zjfheart/Geometry-aware-Instance-reweighted-Adversarial-Training>

Journal ref International Conference on Learning Representations (ICLR 2021)

详情

展开后加载摘要…

URL PDF HTML 收藏
2011.01143 2021-06-01 cs.SD cs.CV eess.AS

Into the Wild with AudioScope: Unsupervised Audio-Visual Separation of On-Screen Sounds

Efthymios Tzinis, Scott Wisdom, Aren Jansen, Shawn Hershey, Tal Remez, Daniel P. W. Ellis, John R. Hershey

Comments ICLR 2021, 27 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2010.08762 2021-06-01 cs.CR cs.AI

Layer-wise Characterization of Latent Information Leakage in Federated Learning

Fan Mo, Anastasia Borovykh, Mohammad Malekzadeh, Hamed Haddadi, Soteris Demetriou

Comments 9 pages, at ICLR workshop (Distributed and Private Machine Learning)

详情

展开后加载摘要…

URL PDF HTML 收藏
2009.13845 2021-06-01 cs.CL cs.AI

GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing

Tao Yu, Chien-Sheng Wu, Xi Victoria Lin, Bailin Wang, Yi Chern Tan, Xinyi Yang, Dragomir Radev, Richard Socher, Caiming Xiong

Comments 16 pages; Accepted to ICLR 2021

详情

展开后加载摘要…

URL PDF HTML 收藏
2105.13962 2021-05-31 cs.CV cs.RO

NViSII: A Scriptable Tool for Photorealistic Image Generation

Nathan Morrical, Jonathan Tremblay, Yunzhi Lin, Stephen Tyree, Stan Birchfield, Valerio Pascucci, Ingo Wald

Comments SDG Workshop at ICLR 2021. Project page is at https://github.com/owl-project/NVISII

详情

展开后加载摘要…

URL PDF HTML 收藏
2104.00479 2021-05-27 cs.LG cs.AI

Towards creativity characterization of generative models via group-based subset scanning

Celia Cintas, Payel Das, Brian Quanz, Skyler Speakman, Victor Akinwande, Pin-Yu Chen

Comments Synthetic Data Generation Workshop at ICLR'21

详情

展开后加载摘要…

URL PDF HTML 收藏
2105.10948 2021-05-25 cs.LG cs.CR stat.ML

Regularization Can Help Mitigate Poisoning Attacks... with the Right Hyperparameters

Javier Carnerero-Cano, Luis Muñoz-González, Phillippa Spencer, Emil C. Lupu

Comments Published at ICLR 2021 Workshop on Security and Safety in Machine Learning Systems. arXiv admin note: text overlap with arXiv:2003.00040

详情

展开后加载摘要…

URL PDF HTML 收藏
2105.10762 2021-05-25 cs.LG cs.AI

AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Fly

Yuchen Jin, Tianyi Zhou, Liangyu Zhao, Yibo Zhu, Chuanxiong Guo, Marco Canini, Arvind Krishnamurthy

Comments Published as a conference paper at ICLR 2021

详情

展开后加载摘要…

URL PDF HTML 收藏