NeurIPS

Metric Space Magnitude for Evaluating the Diversity of Latent Representations

Katharina Limbeck, Rayna Andreeva, Rik Sarkar, Bastian Rieck

Comments Accepted at the 38th Conference on Neural Information Processing Systems (NeurIPS) 2024. The code for computing magnitude is available at https://github.com/aidos-lab/magnipy

Big Batch Bayesian Active Learning by Considering Predictive Probabilities

Sebastian W. Ober, Samuel Power, Tom Diethe, Henry B. Moss

Comments 7 pages, 2 figures; presented as a lightning talk at the NeurIPS Workshop on Bayesian Decision-making and Uncertainty (BDU; 2024)

Globally Convergent Variational Inference

Declan McNamara, Jackson Loper, Jeffrey Regier

Comments Accepted to the 38th Conference on Neural Information Processing Systems (NeurIPS 2024)

Learning Symmetries via Weight-Sharing with Doubly Stochastic Tensors

Putri A. van der Linden, Alejandro García-Castellanos, Sharvaree Vadgama, Thijs P. Kuipers, Erik J. Bekkers

Comments 19 pages, 14 figures, 4 tables

Journal ref Advances in Neural Information Processing Systems (NeurIPS) 2024

What type of inference is planning?

Miguel Lázaro-Gredilla, Li Yang Ku, Kevin P. Murphy, Dileep George

Comments Camera-ready version update

Journal ref Advances in Neural Information Processing Systems, 2024

HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models

Bernal Jiménez Gutiérrez, Yiheng Shu, Yu Gu, Michihiro Yasunaga, Yu Su

Comments NeurIPS 2024. Code and data: https://github.com/OSU-NLP-Group/HippoRAG

EPIC: Effective Prompting for Imbalanced-Class Data Synthesis in Tabular Data Classification via Large Language Models

Jinhee Kim, Taesung Kim, Jaegul Choo

Comments NeurIPS 2024

Directional Smoothness and Gradient Methods: Convergence and Adaptivity

Aaron Mishkin, Ahmed Khaled, Yuanhao Wang, Aaron Defazio, Robert M. Gower

Comments Published as a poster at NeurIPS 2024

Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad

Sayantan Choudhury, Nazarii Tupitsa, Nicolas Loizou, Samuel Horvath, Martin Takac, Eduard Gorbunov

Comments 32 pages, 12 figures

Journal ref The Thirty-Eighth Annual Conference on Neural Information Processing Systems, 2024

Improved off-policy training of diffusion samplers

Marcin Sendera, Minsu Kim, Sarthak Mittal, Pablo Lemos, Luca Scimeca, Jarrid Rector-Brooks, Alexandre Adam, Yoshua Bengio, Nikolay Malkin

Comments NeurIPS 2024; code: https://github.com/GFNOrg/gfn-diffusion

A Closer Look at AUROC and AUPRC under Class Imbalance

Matthew B. A. McDermott, Haoran Zhang, Lasse Hyldig Hansen, Giovanni Angelotti, Jack Gallifant

Comments NeurIPS 2024 (https://openreview.net/forum?id=S3HvA808gk)

Amortizing intractable inference in diffusion models for vision, language, and control

Siddarth Venkatraman, Moksh Jain, Luca Scimeca, Minsu Kim, Marcin Sendera, Mohsin Hasan, Luke Rowe, Sarthak Mittal, Pablo Lemos, Emmanuel Bengio, Alexandre Adam, Jarrid Rector-Brooks, Yoshua Bengio, Glen Berseth, Nikolay Malkin

Comments NeurIPS 2024; code: https://github.com/GFNOrg/diffusion-finetuning

Hybrid Top-Down Global Causal Discovery with Local Search for Linear and Nonlinear Additive Noise Models

Sujai Hiremath, Jacqueline R. M. A. Maasch, Mengxiao Gao, Promit Ghosal, Kyra Gan

Comments To appear at the Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS 2024)

Benchmarking Counterfactual Image Generation

Thomas Melistas, Nikos Spyrou, Nefeli Gkouti, Pedro Sanchez, Athanasios Vlontzos, Yannis Panagakis, Giorgos Papanastasiou, Sotirios A. Tsaftaris

Comments Published as a conference paper at NeurIPS 2024 Datasets and Benchmarks Track https://openreview.net/forum?id=0T8xRFrScB Project page: https://gulnazaki.github.io/counterfactual-benchmark

Journal ref The Thirty-eight Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2024)

Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning

Lanqing Li, Hai Zhang, Xinyu Zhang, Shatong Zhu, Yang Yu, Junqiao Zhao, Pheng-Ann Heng

Comments 26 pages, 8 figures, 7 tables. TLDR: We propose a novel information theoretic framework of the context-based offline meta-RL paradigm, which unifies several mainstream methods and leads to two robust algorithm implementations

Journal ref 38th Conference on Neural Information Processing Systems (NeurIPS 2024)

Risk-Averse Finetuning of Large Language Models

Sapana Chaudhary, Ujwal Dinesha, Dileep Kalathil, Srinivas Shakkottai

Comments Neurips 2024

Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learning

Hanwen Zhong, Jiaxin Chen, Yutong Zhang, Di Huang, Yunhong Wang

Comments Accepted by the 38th Conference on Neural Information Processing Systems (NeurIPS 2024)

Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency model

Jing Zhang, Linjiajie Fang, Kexin Shi, Wenjia Wang, Bing-Yi Jing

Comments Neurips 2024

Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation

Jiaxin Cheng, Zixu Zhao, Tong He, Tianjun Xiao, Yicong Zhou, Zheng Zhang

Comments Accepted in NeurIPS 2024

Modeling Latent Neural Dynamics with Gaussian Process Switching Linear Dynamical Systems

Amber Hu, David Zoltowski, Aditya Nair, David Anderson, Lea Duncker, Scott Linderman

Comments 38th Conference on Neural Information Processing Systems (NeurIPS 2024)

MLLM-CompBench: A Comparative Reasoning Benchmark for Multimodal LLMs

Jihyung Kil, Zheda Mai, Justin Lee, Zihe Wang, Kerrie Cheng, Lemeng Wang, Ye Liu, Arpita Chowdhury, Wei-Lun Chao

Comments This paper has been accepted to NeurIPS 2024. The first two authors contributed equally to this work

SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers

Shraman Pramanick, Rama Chellappa, Subhashini Venugopalan

Comments NeurIPS 2024, Datasets & Benchmarks track

Safety through feedback in Constrained RL

Shashank Reddy Chirra, Pradeep Varakantham, Praveen Paruchuri

Comments Accepted at NeurIPS 2024 (Poster)

Rough Transformers: Lightweight and Continuous Time Series Modelling through Signature Patching

Fernando Moreno-Pino, Álvaro Arroyo, Harrison Waldon, Xiaowen Dong, Álvaro Cartea

Comments NeurIPS 2024 Conference (Camera Ready Version)

Improving Linear System Solvers for Hyperparameter Optimisation in Iterative Gaussian Processes

Jihao Andreas Lin, Shreyas Padhy, Bruno Mlodozeniec, Javier Antorán, José Miguel Hernández-Lobato

Comments Advances in Neural Information Processing Systems 2024

Annealing Machine-assisted Learning of Graph Neural Network for Combinatorial Optimization

Pablo Loyola, Kento Hasegawa, Andres Hoyos-Idobro, Kazuo Ono, Toyotaro Suzumura, Yu Hirate, Masanao Yamaoka

Comments Second Workshop on Machine Learning with New Compute Paradigms at NeurIPS 2024 (MLNCP 2024)

4-bit Shampoo for Memory-Efficient Network Training

Sike Wang, Pan Zhou, Jia Li, Hua Huang

Comments NeurIPS 2024 final camera-ready revisions, rectify the legend in figure 9

Self-supervised video pretraining yields robust and more human-aligned visual representations

Nikhil Parthasarathy, S. M. Ali Eslami, João Carreira, Olivier J. Hénaff

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

Analog Bayesian neural networks are insensitive to the shape of the weight distribution

Ravi G. Patel, T. Patrick Xiao, Sapan Agarwal, Christopher Bennett

Comments Presented at the NeurIPS 2024 Workshop on Machine Learning with New Compute Paradigms, https://openreview.net/forum?id=soS5qgU7Yb

The GAN is dead; long live the GAN! A Modern GAN Baseline

Yiwen Huang, Aaron Gokaslan, Volodymyr Kuleshov, James Tompkin

Comments Accepted to NeurIPS 2024. Code available at https://github.com/brownvc/R3GAN/