ICML

Towards Fine-grained Visual Representations by Combining Contrastive Learning with Image Reconstruction and Attention-weighted Pooling

Jonas Dippel, Steffen Vogler, Johannes Höhne

Comments ICML 2021 Workshop: Self-Supervised Learning for Reasoning and Perception

Neural Ensemble Search for Uncertainty Estimation and Dataset Shift

Sheheryar Zaidi, Arber Zela, Thomas Elsken, Chris Holmes, Frank Hutter, Yee Whye Teh

Comments Accepted at NeurIPS 2021; earlier version of this work was accepted for oral presentation at ICML 2020 Workshop on Uncertainty & Robustness in Deep Learning

Structured second-order methods via natural gradient descent

Wu Lin, Frank Nielsen, Mohammad Emtiyaz Khan, Mark Schmidt

Comments Fixed some typos and added a new figure. ICML 2021 workshop paper. A short version of arXiv:2102.07405 with a focus on optimization tasks

Network Inference and Influence Maximization from Samples

Zhijie Zhang, Wei Chen, Xiaoming Sun, Jialin Zhang

Comments Parellel results about the LT model are added to the conference (ICML 2021) version

Offline Preference-Based Apprenticeship Learning

Daniel Shin, Daniel S. Brown, Anca D. Dragan

Comments ICML Workshop on Human-AI Collaboration in Sequential Decision-Making, 2021

SwiftLane: Towards Fast and Efficient Lane Detection

Oshada Jayasinghe, Damith Anhettigama, Sahan Hemachandra, Shenali Kariyawasam, Ranga Rodrigo, Peshala Jayasekara

Comments Accepted to 20th IEEE International Conference on Machine Learning and Applications (ICMLA) 2021

Large-Scale Meta-Learning with Continual Trajectory Shifting

Jaewoong Shin, Hae Beom Lee, Boqing Gong, Sung Ju Hwang

Journal ref Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9603-9613, 2021

Deep Semi-Supervised Learning for Time Series Classification

Jann Goschenhofer, Rasmus Hvingelby, David Rügamer, Janek Thomas, Moritz Wagner, Bernd Bischl

Journal ref 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)

FILTRA: Rethinking Steerable CNN by Filter Transform

Bo Li, Qili Wang, Gim Hee Lee

Comments ICML 2021

On Reward-Free RL with Kernel and Neural Function Approximations: Single-Agent MDP and Markov Game

Shuang Qiu, Jieping Ye, Zhaoran Wang, Zhuoran Yang

Comments ICML 2021

Dual-CLVSA: a Novel Deep Learning Approach to Predict Financial Markets with Sentiment Measurements

Jia Wang, Hongwei Zhu, Jiancheng Shen, Yu Cao, Benyuan Liu

Comments 8 pages, 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA). IEEE, 2021

Sea Ice Forecasting using Attention-based Ensemble LSTM

Sahara Ali, Yiyi Huang, Xin Huang, Jianwu Wang

Comments Accepted by the Tackling Climate Change with Machine Learning Workshop at the 2021 International Conference on Machine Learning (ICML 2021)

Exploration with Multi-Sample Target Values for Distributional Reinforcement Learning

Michael Teng, Michiel van de Panne, Frank Wood

Comments Submitted to ICML 2022

An Adapter Based Pre-Training for Efficient and Scalable Self-Supervised Speech Representation Learning

Samuel Kessler, Bethan Thomas, Salah Karout

Comments 5 pages, 6 figures. Accepted at ICASSP 2022. This version replaces an earlier version of paper accepted at an ICML 2021 workshop

Opening the Blackbox: Accelerating Neural Differential Equations by Regularizing Internal Solver Heuristics

Avik Pal, Yingbo Ma, Viral Shah, Christopher Rackauckas

Comments Proceedings of the 38 th International Conference on Machine Learning, 2021

Journal ref International Conference on Machine Learning, 139 (2021), 8325-8335

Novelty-based Generalization Evaluation for Traffic Light Detection

Arvind Kumar Shekar, Laureen Lake, Liang Gou, Liu Ren

Comments Accepted/Presented at ICMLA 2021

Journal ref 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)

Neural Transformation Learning for Deep Anomaly Detection Beyond Images

Chen Qiu, Timo Pfrommer, Marius Kloft, Stephan Mandt, Maja Rudolph

Journal ref Proceedings of the 38th International Conference on Machine Learning, 2021, volume:139, pages:8703--8714

Quantifying Ignorance in Individual-Level Causal-Effect Estimates under Hidden Confounding

Andrew Jesson, Sören Mindermann, Yarin Gal, Uri Shalit

Comments 19 pages, 5 figures, ICML 2021

Journal ref PMLR 139 (2021) 4829-4838

Protum: A New Method For Prompt Tuning Based on "[MASK]"

Pan He, Yuxi Chen, Yan Wang, Yanru Zhang

Comments under review in ICML

LIDSNet: A Lightweight on-device Intent Detection model using Deep Siamese Network

Vibhav Agarwal, Sudeep Deepak Shivnikar, Sourav Ghosh, Himanshu Arora, Yashwant Saini

Comments Accepted for publication in 2021 IEEE 20th International Conference on Machine Learning and Applications (ICMLA)

Journal ref 2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA), Pasadena, CA, USA, 2021, pp. 1112-1117

Financial Markets Prediction with Deep Learning

Jia Wang, Tong Sun, Benyuan Liu, Yu Cao, Degang Wang

Comments 8 pages, 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA). IEEE, 2018

FOD-A: A Dataset for Foreign Object Debris in Airports

Travis Munyer, Pei-Chi Huang, Chenyu Huang, Xin Zhong

Comments This paper has been accepted for publication by 20th IEEE International Conference on Machine Learning and Applications. The copyright is with the IEEE

Soft BIBD and Product Gradient Codes

Animesh Sakorikar, Lele Wang

Comments New results in Section III-A and Section IV, references added. Presented in part at the IEEE International Symposiums on Topics in Coding (ISTC) 2021 and in part at the Information-Theoretic Methods for Rigorous, Responsible, and Reliable Machine Learning (ITR3) Workshop in International Conference on Machine Learning (ICML) 2021

Follow-the-Regularized-Leader Routes to Chaos in Routing Games

Jakub Bielawski, Thiparat Chotibut, Fryderyk Falniowski, Grzegorz Kosiorowski, Michał Misiurewicz, Georgios Piliouras

Comments 30 pages, 8 figures

Journal ref Proceedings of the 38th International Conference on Machine Learning, PMLR 139:925-935, 2021

Dense for the Price of Sparse: Improved Performance of Sparsely Initialized Networks via a Subspace Offset

Ilan Price, Jared Tanner

Comments 18 pages, 15 figures

Journal ref Proceedings of the 38th International Conference on Machine Learning, PMLR 139:8620-8629, 2020

Time Limits in Reinforcement Learning

Fabio Pardo, Arash Tavakoli, Vitaly Levdik, Petar Kormushev

Comments ICML 2018, NIPS 2017 Deep RL Symposium, code and videos: https://sites.google.com/view/time-limits-in-rl

Journal ref PMLR 80: 4042-4051 (2018)

DRTCI: Learning Disentangled Representations for Temporal Causal Inference

Garima Gupta, Lovekesh Vig, Gautam Shroff

Comments Accepted in Workshop on "The Neglected Assumptions in Causal Inference" at ICML 2021 (July)

Hierarchical VAEs Know What They Don't Know

Jakob D. Havtorn, Jes Frellsen, Søren Hauberg, Lars Maaløe

Comments Appeared in Proceedings of the 38th International Conference on Machine Learning (ICML 2021). 18 pages, source code available at https://github.com/JakobHavtorn/hvae-oodd, https://github.com/vlievin/biva-pytorch and https://github.com/larsmaaloee/BIVA

Tractable structured natural gradient descent using local parameterizations

Wu Lin, Frank Nielsen, Mohammad Emtiyaz Khan, Mark Schmidt

Comments An extended version of the ICML 2021 paper. Note: A workshop (short) paper with a focus on optimization tasks can be found at arXiv:2107.10884

Voice2Series: Reprogramming Acoustic Models for Time Series Classification

Chao-Han Huck Yang, Yun-Yun Tsai, Pin-Yu Chen

Comments Updated version with a correction. The full draft was submitted in Jan 2021. The Voice2Series project initially was launched in Sep 2020. Accepted to ICML 2021, 16 Pages

Journal ref Proceedings of the 38th International Conference on Machine Learning 2021