NeurIPS

Mean-Field Assisted Deep Boltzmann Learning with Probabilistic Computers

Shuvro Chowdhury, Shaila Niazi, Kerem Y. Camsari

Journal ref Workshop on Machine Learning with New Compute Paradigms at NeurIPS 2023(MLNCP 2023)

Real-Time FJ/MAC PDE Solvers via Tensorized, Back-Propagation-Free Optical PINN Training

Yequan Zhao, Xian Xiao, Xinling Yu, Ziyue Liu, Zhixiong Chen, Geza Kurczveil, Raymond G. Beausoleil, Zheng Zhang

Comments ML with New Compute Paradigms (MLNCP) at NeurIPS 2023

DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification

Mintong Kang, Dawn Song, Bo Li

Comments Accepted to NeurIPS 2023

CBD: A Certified Backdoor Detector Based on Local Dominant Probability

Zhen Xiang, Zidi Xiong, Bo Li

Comments Accepted to NeurIPS 2023

Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentation

Yun Xing, Jian Kang, Aoran Xiao, Jiahao Nie, Ling Shao, Shijian Lu

Comments NeurIPS 2023. Code is available at https://github.com/xing0047/rewrite

Dynamically Masked Discriminator for Generative Adversarial Networks

Wentian Zhang, Haozhe Liu, Bing Li, Jinheng Xie, Yawen Huang, Yuexiang Li, Yefeng Zheng, Bernard Ghanem

Comments Updated v2 -- NeurIPS 2023 camera ready version

Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behavior

Shashank Subramanian, Peter Harrington, Kurt Keutzer, Wahid Bhimji, Dmitriy Morozov, Michael Mahoney, Amir Gholami

Comments 16 pages, 11 figures

Journal ref NeurIPS 2023

Optimal cross-learning for contextual bandits with unknown context distributions

Jon Schneider, Julian Zimmert

Comments Appeared at NeurIPS 2023

Understanding the Detrimental Class-level Effects of Data Augmentation

Polina Kirichenko, Mark Ibrahim, Randall Balestriero, Diane Bouchacourt, Ramakrishna Vedantam, Hamed Firooz, Andrew Gordon Wilson

Comments Neural Information Processing Systems (NeurIPS), 2023

Glance and Focus: Memory Prompting for Multi-Event Video Question Answering

Ziyi Bai, Ruiping Wang, Xilin Chen

Comments Accepted in NeurIPS 2023

Accelerating Black-Box Molecular Property Optimization by Adaptively Learning Sparse Subspaces

Farshud Sorourifar, Thomas Banker, Joel A. Paulson

Comments 9 pages, 2 figures consisting of 6 and 4 plots, accepted to NeurIPS 2023 Workshop on Adaptive Experimental Design and Active Learning in the Real World

Navigating Data Heterogeneity in Federated Learning A Semi-Supervised Federated Object Detection

Taehyeon Kim, Eric Lin, Junu Lee, Christian Lau, Vaikkunth Mugunthan

Comments NeurIPS 2023

SPEED: Speculative Pipelined Execution for Efficient Decoding

Coleman Hooper, Sehoon Kim, Hiva Mohammadzadeh, Hasan Genc, Kurt Keutzer, Amir Gholami, Sophia Shao

Comments NeurIPS Workshop on Efficient Natural Language and Speech Processing (2023)

Depth-discriminative Metric Learning for Monocular 3D Object Detection

Wonhyeok Choi, Mingyu Shin, Sunghoon Im

Comments Accepted at NeurIPS 2023

The Cambridge Law Corpus: A Dataset for Legal AI Research

Andreas Östling, Holli Sargeant, Huiyuan Xie, Ludwig Bull, Alexander Terenin, Leif Jonsson, Måns Magnusson, Felix Steffek

Journal ref Advances in Neural Information Processing Systems, Datasets and Benchmarks Track, 2023

When Do Graph Neural Networks Help with Node Classification? Investigating the Impact of Homophily Principle on Node Distinguishability

Sitao Luan, Chenqing Hua, Minkai Xu, Qincheng Lu, Jiaqi Zhu, Xiao-Wen Chang, Jie Fu, Jure Leskovec, Doina Precup

Comments Accepted by 37th Conference on Neural Information Processing Systems (NeurIPS 2023)

The Contextual Lasso: Sparse Linear Models via Deep Neural Networks

Ryan Thompson, Amir Dezfouli, Robert Kohn

Comments To appear in Advances in Neural Information Processing Systems

A Compact Representation for Bayesian Neural Networks By Removing Permutation Symmetry

Tim Z. Xiao, Weiyang Liu, Robert Bamler

Comments Accepted at NeurIPS 2023 Workshop on Unifying Representations in Neural Models; 4 pages + appendix

A Novel Explanation Against Linear Neural Networks

Anish Lakkapragada

Comments Accepted for NeurIPS 2023, New in ML Workshop

Forbidden Facts: An Investigation of Competing Objectives in Llama-2

Tony T. Wang, Miles Wang, Kaivalya Hariharan, Nir Shavit

Comments Accepted to the ATTRIB and SoLaR workshops at NeurIPS 2023; (v3: clarified experimental details)

On the Interplay Between Stepsize Tuning and Progressive Sharpening

Vincent Roulet, Atish Agarwala, Fabian Pedregosa

Comments Presented at the NeurIPS 2023 OPT Wokshop

Optimizing Inventory Routing: A Decision-Focused Learning Approach using Neural Networks

MD Shafikul Islam, Azmine Toushik Wasi

Comments 3 Pages, 2 figures, New in ML Workshop at NeurIPS 2023. Openreview forum: https://openreview.net/forum?id=r0fzjB8f7f&

Journal ref New in Machine Learning Workshop, NeurIPS 2023

The Data Conversion Bottleneck in Analog Computing Accelerators

James T. Meech, Vasileios Tsoutsouras, Phillip Stanley-Marbell

Comments Accepted to the First Workshop on Machine Learning with New Compute Paradigms at NeurIPS 2023 (MLNPCP 2023)

Addressing Negative Transfer in Diffusion Models

Hyojun Go, JinYoung Kim, Yunsung Lee, Seunghyun Lee, Shinhyeok Oh, Hyeongdon Moon, Seungtaek Choi

Comments Neurips 2023. Project page: https://gohyojun15.github.io/ANT_diffusion/

CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion

Guangyao Zhai, Evin Pınar Örnek, Shun-Cheng Wu, Yan Di, Federico Tombari, Nassir Navab, Benjamin Busam

Comments NeurIPS 2023 camera-ready

Energy-Based Sliced Wasserstein Distance

Khai Nguyen, Nhat Ho

Comments Accepted to NeurIPS 2023, 30 pages, 8 figures, 6 tables

Markovian Sliced Wasserstein Distances: Beyond Independent Projections

Khai Nguyen, Tongzheng Ren, Nhat Ho

Comments Accepted to NeurIPS 2023, 29 pages, 8 figures, 5 tables

Generalization properties of contrastive world models

Kandan Ramakrishnan, R. James Cotton, Xaq Pitkow, Andreas S. Tolias

Comments Accepted at the NeurIPS 2023 Workshop: Self-Supervised Learning - Theory and Practice

Beyond PID Controllers: PPO with Neuralized PID Policy for Proton Beam Intensity Control in Mu2e

Chenwei Xu, Jerry Yao-Chieh Hu, Aakaash Narayanan, Mattson Thieme, Vladimir Nagaslaev, Mark Austin, Jeremy Arnold, Jose Berlioz, Pierrick Hanlet, Aisha Ibrahim, Dennis Nicklaus, Jovan Mitrevski, Jason Michael St. John, Gauri Pradhan, Andrea Saewert, Kiyomi Seiya, Brian Schupbach, Randy Thurman-Keup, Nhan Tran, Rui Shi, Seda Ogrenci, Alexis Maya-Isabelle Shuping, Kyle Hazelwood, Han Liu

Comments 10 pages, accepted at NeurIPS 2023 ML4Phy Workshop

Gradient Flossing: Improving Gradient Descent through Dynamic Control of Jacobians

Rainer Engelken

Comments 28 pages, 16 figures, accepted at NeurIPS 2023