ICLR - arXivDaily 期刊&会议

2210.01078 2023-03-14 cs.LG cs.AI

Unsupervised Model Selection for Time-series Anomaly Detection

Mononito Goswami, Cristian Challu, Laurent Callot, Lenon Minorics, Andrey Kan

Comments Accepted at International Conference on Learning Representations (ICLR) 2023 with a notable-top-25% recommendation. Reviewer, AC and author discussion available at https://openreview.net/forum?id=gOZ_pKANaPW

2210.00638 2023-03-14 cs.LG physics.data-an

What shapes the loss landscape of self-supervised learning?

Liu Ziyin, Ekdeep Singh Lubana, Masahito Ueda, Hidenori Tanaka

Comments Published at ICLR 2023

2203.12023 2023-03-14 cs.LG cs.AI cs.CV stat.ML

Generative Modeling Helps Weak Supervision (and Vice Versa)

Benedikt Boecking, Nicholas Roberts, Willie Neiswanger, Stefano Ermon, Frederic Sala, Artur Dubrawski

Comments Published as a conference paper at ICLR 2023

2202.00395 2023-03-14 cs.LG stat.ML

Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification

Takashi Ishida, Ikko Yamane, Nontawat Charoenphakdee, Gang Niu, Masashi Sugiyama

Comments ICLR 2023 (notable-top-5%)

2303.05641 2023-03-13 cs.LG cs.AI

Efficient Real Time Recurrent Learning through combined activity and parameter sparsity

Anand Subramoney

Comments Published as a workshop paper at ICLR 2023 Workshop on Sparsity in Neural Networks

2303.05593 2023-03-13 cs.LG cs.AI cs.CR

Learning the Wrong Lessons: Inserting Trojans During Knowledge Distillation

Leonard Tang, Tom Shlomi, Alexander Cai

Comments ICLR 2023 Workshop on Backdoor Attacks and Defenses in Machine Learning

2303.05552 2023-03-13 cs.CV cs.LG

EfficientTempNet: Temporal Super-Resolution of Radar Rainfall

Bekir Z Demiray, Muhammed Sit, Ibrahim Demir

Comments Published as a workshop paper at Tackling Climate Change with Machine Learning, ICLR 2023

2301.10418 2023-03-13 cs.LG cs.AI cs.CV

DEJA VU: Continual Model Generalization For Unseen Domains

Chenxi Liu, Lixu Wang, Lingjuan Lyu, Chen Sun, Xiao Wang, Qi Zhu

Comments Published as a conference paper at ICLR 2023

2211.10257 2023-03-13 cs.LG stat.ML

Model-based Causal Bayesian Optimization

Scott Sussex, Anastasiia Makarova, Andreas Krause

Comments 24 pages, 8 figures, accepted at ICLR 2023

2210.13066 2023-03-13 cs.RO

DaXBench: Benchmarking Deformable Object Manipulation with Differentiable Physics

Siwei Chen, Yiqing Xu, Cunjun Yu, Linfeng Li, Xiao Ma, Zhongwen Xu, David Hsu

Comments ICLR 2023 (Oral)

2210.03629 2023-03-13 cs.CL cs.AI cs.LG

ReAct: Synergizing Reasoning and Acting in Language Models

Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, Yuan Cao

Comments v3 is the ICLR camera ready version with some typos fixed. Project site with code: https://react-lm.github.io

2208.07227 2023-03-13 cs.CV cs.AI cs.GR cs.LG cs.RO

DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images

Bing Wang, Lu Chen, Bo Yang

Comments ICLR 2023. Our data and code are available at: https://github.com/vLAR-group/DM-NeRF

2206.15369 2023-03-13 cs.CV cs.LG

No Reason for No Supervision: Improved Generalization in Supervised Models

Mert Bulent Sariyildiz, Yannis Kalantidis, Karteek Alahari, Diane Larlus

Comments Accepted to ICLR 2023 (spotlight)

2206.06178 2023-03-13 cs.LG cs.AI cs.NE

Efficient recurrent architectures through activity sparsity and sparse back-propagation through time

Anand Subramoney, Khaleelulla Khan Nazeer, Mark Schöne, Christian Mayr, David Kappel

Comments Published as notable-top-25% paper in ICLR 2023

2106.00553 2023-03-13 cs.LG stat.ML

SHINE: SHaring the INverse Estimate from the forward pass for bi-level optimization and implicit models

Zaccharie Ramzi, Florian Mannel, Shaojie Bai, Jean-Luc Starck, Philippe Ciuciu, Thomas Moreau

Comments Accepted as a spotlight to ICLR 2022

2303.05512 2023-03-10 cs.CV cs.AI cs.GR cs.LG cs.RO

PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification

Xuan Li, Yi-Ling Qiao, Peter Yichen Chen, Krishna Murthy Jatavallabhula, Ming Lin, Chenfanfu Jiang, Chuang Gan

Comments ICLR 2023 Spotlight. Project page: https://sites.google.com/view/PAC-NeRF

2303.05510 2023-03-10 cs.LG cs.AI cs.CL cs.PL

Planning with Large Language Models for Code Generation

Shun Zhang, Zhenfang Chen, Yikang Shen, Mingyu Ding, Joshua B. Tenenbaum, Chuang Gan

Comments ICLR 2023. Project page:https://codeaimcts.github.io

2303.05506 2023-03-10 cs.LG cs.AI stat.ML

TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization

Alan Jeffares, Tennison Liu, Jonathan Crabbé, Fergus Imrie, Mihaela van der Schaar

Comments Published at International Conference on Learning Representations (ICLR) 2023

2303.05498 2023-03-10 cs.LG cs.AI cs.CR cs.CV

Mark My Words: Dangers of Watermarked Images in ImageNet

Kirill Bykov, Klaus-Robert Müller, Marina M. -C. Höhne

Comments 5 pages, 4 figures, Accepted to the ICLR 2023 TrustML-(un)Limited workshop

2303.05370 2023-03-10 cs.CV

Rethinking Self-Supervised Visual Representation Learning in Pre-training for 3D Human Pose and Shape Estimation

Hongsuk Choi, Hyeongjin Nam, Taeryung Lee, Gyeongsik Moon, Kyoung Mu Lee

Comments Accepted to ICLR 2023, 18 pages including the appendix

2303.05148 2023-03-10 cs.CV stat.ML

Weakly Supervised Knowledge Transfer with Probabilistic Logical Reasoning for Object Detection

Martijn Oldenhof, Adam Arany, Yves Moreau, Edward De Brouwer

Comments Accepted to ICLR 2023

2303.04809 2023-03-10 cs.LG cs.AI cs.CY cs.HC

Learning Human-Compatible Representations for Case-Based Decision Support

Han Liu, Yizhou Tian, Chacha Chen, Shi Feng, Yuxin Chen, Chenhao Tan

Comments Accepted at ICLR 2023

2303.01215 2023-03-10 cs.LG

Why (and When) does Local SGD Generalize Better than SGD?

Xinran Gu, Kaifeng Lyu, Longbo Huang, Sanjeev Arora

Comments Published as a conference paper at ICLR 2023

2302.02914 2023-03-10 cs.LG cs.AI cs.SI

Energy-based Out-of-Distribution Detection for Graph Neural Networks

Qitian Wu, Yiting Chen, Chenxiao Yang, Junchi Yan

Comments Published at ICLR 2023, the implementation code is available at https://github.com/qitianwu/GraphOOD-GNNSafe

2301.13510 2023-03-10 cs.CV cs.AI

3D Former: Monocular Scene Reconstruction with 3D SDF Transformers

Weihao Yuan, Xiaodong Gu, Heng Li, Zilong Dong, Siyu Zhu

Comments Accepted to ICLR 2023

2209.15571 2023-03-10 cs.LG stat.ML

Building Normalizing Flows with Stochastic Interpolants

Michael S. Albergo, Eric Vanden-Eijnden

Comments ICLR 2023

2209.15162 2023-03-10 cs.CL cs.LG

Linearly Mapping from Image to Text Space

Jack Merullo, Louis Castricato, Carsten Eickhoff, Ellie Pavlick

Comments Accepted at ICLR 2023

2209.09117 2023-03-10 cs.CV cs.CR cs.LG

Part-Based Models Improve Adversarial Robustness

Chawin Sitawarin, Kornrapat Pongmala, Yizheng Chen, Nicholas Carlini, David Wagner

Comments Published in ICLR 2023 (poster). Code can be found at https://github.com/chawins/adv-part-model

2209.03694 2023-03-10 cs.CV cs.LG

Aerial View Localization with Reinforcement Learning: Towards Emulating Search-and-Rescue

Aleksis Pirinen, Anton Samuelsson, John Backsund, Kalle Åström

Comments Accepted to ICLR 2023 Workshop on Machine Learning for Remote Sensing

2202.11202 2023-03-10 cs.LG cs.AI cs.CR cs.CV

Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning

Hao He, Kaiwen Zha, Dina Katabi

Comments ICLR 2023 Spotlight (notable top 25%). The first two authors contributed equally to this paper