Google at ICML 2024

Perturb-and-Project: Differentially Private Similarities and Marginals
Vincent Cohen-Addad, Tommaso d'Orsi, Alessandro Epasto, Vahab Mirrokni, Peilin Zhong

Replicable Learning of Large-Margin Halfspaces
Alkis Kalavasis, Amin Karbasi, Kasper Green Larsen, Grigoris Velegkas, Felix Zhou

Decoding-time Realignment of Language Models
Tianlin Liu, Shangmin Guo, Leonardo Bianco*, Daniele Calandriello, Quentin Berthet, Felipe Llinares-López, Jessica Hoffmann, Lucas Dixon, Michal Valko, Mathieu Blondel

Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation
Fengdi Che, Chenjun Xiao, Jincheng Mei, Bo Dai, Ramki Gummadi, Oscar A Ramirez*, Christopher K Harris*,
A. Rupam Mahmood, Dale Schuurmans

Dynamic Correlation Clustering in Sublinear Update Time
Vincent Cohen-Addad, Silvio Lattanzi, Andreas Maggiori, Nikos Parotsidis

PriorBoost: An Adaptive Algorithm for Learning from Aggregate Responses
Adel Javanmard, Matthew Fahrbach, Vahab Mirrokni

How Free is Parameter-Free Stochastic Optimization?
Amit Attia, Tomer Koren

Practical Performance Guarantees for Pipelined DNN Inference
Aaron Archer, Matthew Fahrbach, Kuikui Liu, Prakash Prabhu

Regression with Multi-Expert Deferral
Anqi Mao, Mehryar Mohri, Yutao Zhong

Data-Efficient Learning via Clustering-Based Sensitivity Sampling: Foundation Models and Beyond
Kyriakos Axiotis, Vincent Cohen-Addad, Monika Henzinger, Sammy Jerome, Vahab Mirrokni, David Saulpic, David Woodruff, Michael Wunder

Isometric Representation Learning for Disentangled Latent Space of Diffusion Models
Jaehoon Hahm, Junho Lee, Sunghyun Kim, Joonseok Lee

Learning from Students: Applying t-Distributions to Explore Accurate and Efficient Formats for LLMs
Jordan Dotzel, Yuzong Chen, Bahaa Kotb, Sushma Prasad, Gang Wu, Sheng Li, Mohamed S. Abdelfattah, Zhiru Zhang

LEVI: Generalizable Fine-tuning via Layer-wise Ensemble of Different Views
Yuji Roh, Qingyun Liu, Huan Gui, Zhe Yuan, Yujin Tang, Steven Euijong Whang, Liang Liu, Shuchao Bi,
Lichan Hong, Ed H. Chi, Zhe Zhao

Out of the Ordinary: Spectrally Adapting Regression for Covariate Shift
Benjamin Eyre, Elliot Creager, David Madras, Vardan Papyan, Richard Zemel

Privacy-Preserving Instructions for Aligning Large Language Models
Da Yu*, Peter Kairouz, Sewoong Oh, Zheng Xu

Representation Surgery: Theory and Practice of Affine Steering
Shashwat Singh, Shauli Ravfogel*, Jonathan Herzig, Roee Aharoni, Ryan Cotterell, Ponnurangam Kumaraguru

A Statistical Framework for Data-dependent Retrieval-Augmented Models
Soumya Basu, Ankit Singh Rawat, Manzil Zaheer

Two Heads are Actually Better than One: Towards Better Adversarial Robustness via Transduction and Rejection
Nils Palumbo, Yang Guo, Xi Wu, Jiefeng Chen, Yingyu Liang, Somesh Jha

Bayesian Regret Minimization in Offline Bandits
Marek Petrik, Guy Tennenholtz, Mohammad Ghavamzadeh

Break the Sequential Dependency of LLM Inference Using Lookahead Decoding
Yichao Fu, Peter Bailis, Ion Stoica, Hao Zhang

Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicates
Ashish Hooda*, Mihai Christodorescu, Miltiadis Allamanis, Aaron Wilson, Kassem Fawaz, Somesh Jha

DySLIM: Dynamics Stable Learning by Invariant Measure for Chaotic Systems
Yair Schiff, Zhong Yi Wan, Jeffrey B. Parker, Stephan Hoyer, Volodymyr Kuleshov, Fei Sha, Leonardo Zepeda-Núñez

A Field Guide for Pacing Budget and ROS Constraints
Santiago R. Balseiro, Kshipra Bhawalkar, Zhe Feng, Haihao Lu, Vahab Mirrokni, Balasubramanian Sivan, Di Wang

How Private is DP-SGD?
Lynn Chua, Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Amer Sinha, Chiyuan Zhang

Improved Differentially Private and Lazy Online Convex Optimization: Lower Regret without Smoothness Requirements
Naman Agarwal, Satyen Kale, Karan Singh, Abhradeep Guha Thakurta

LayerMerge: Neural Network Depth Compression through Layer Pruning and Merging
Jinuk Kim, Marwa El Halabi, Mingi Ji, Hyun Oh Song

Learning and Forgetting Unsafe Examples in Large Language Models
Jiachen Zhao, Zhun Deng, David Madras, James Zou, Mengye Ren

A Near-Linear Time Approximation Algorithm for Beyond-Worst-Case Graph Clustering
Vincent Cohen-Addad, Tommaso d'Orsi, Aida Mousavifar

The Non-linear F-Design and Applications to Interactive Learning
Alekh Agarwal, Jian Qian, Alexander Rakhlin, Tong Zhang

Pi-DUAL: Using Privileged Information to Distinguish Clean from Noisy Labels
Ke Wang, Guillermo Ortiz-Jimenez, Rodolphe Jenatton, Mark Collier, Efi Kokiopoulou, Pascal Frossard

Position: Cracking the Code of Cascading Disparity Towards Marginalized Communities
Golnoosh Farnadi, Mohammad Havaei, Negar Rostamzadeh

Unmasking Vulnerabilities: Cardinality Sketches Under Adaptive Inputs
Sara Ahmadian, Edith Cohen

What is Dataset Distillation Learning?
William Yang, Ye Zhu, Zhiwei Deng, Olga Russakovsky

Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?
Khashayar Gatmiry, Nikunj Saunshi, Sashank J. Reddi, Stefanie Jegelka, Sanjiv Kumar

Cell2Sentence: Teaching Large Language Models the Language of Biology
Daniel Levine, Syed A Rizvi, Sacha Lévy, Nazreen Pallikkavaliyaveetil, David Zhang, Xingyu Chen,
Sina Ghadermarzi, Ruiming Wu, Zihe Zheng, Ivan Vrkic, Anna Zhong, Daphne Raskin, Insu Han, Antonio Henrique de Oliveira Fonseca, Josue Ortega Caro, Amin Karbasi, Rahul Madhav Dhodapkar, David van Dijk

Consistent Submodular Maximization
Paul Duetting, Federico Fusco, Silvio Lattanzi, Ashkan Norouzi-Fard, Morteza Zaddimoghadam

Controlled Decoding from Language Models
Sidharth Mudgal, Jong Lee, Harish Ganapathy, YaGuang Li, Tao Wang*, Yanping Huang, Zhifeng Chen, Heng-Tze Cheng, Michael Collins, Trevor Strohman, Jilin Chen, Alex Beutel*, Ahmad Beirami

Differentially Private Domain Adaptation with Theoretical Guarantees
Raef Bassily, Corinna Cortes, Anqi Mao, Mehryar Mohri

Eluder-Based Regret for Stochastic Contextual MDPs
Orin Levy, Asaf Cassel, Alon Cohen, Yishay Mansour

A Minimaximalist Approach to Reinforcement Learning from Human Feedback
Gokul Swamy*, Christoph Dann, Rahul Kidambi, Zhiwei Steven Wu, Alekh Agarwal

Multi-View Stochastic Block Models
Vincent Cohen-Addad, Tommaso d'Orsi, Silvio Lattanzi, Rajai Nasser

Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback
Asaf Cassel, Haipeng Luo, Aviv Rosenberg, Dmitry Sotnikov

Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models (see blog post)
Asma Ghandeharioun, Avi Caciularu, Adam Pearce, Lucas Dixon, Mor Geva

Robust Inverse Graphics via Probabilistic Inference
Tuan Anh Le, Pavel Sountsov, Matthew Douglas Hoffman, Ben Lee, Brian Patton, Rif A. Saurous

Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generation
Mingyuan Zhou, Huangjie Zheng, Zhendong Wang, Mingzhang Yin, Hai Huang

Tandem Transformers for Inference Efficient LLMs
Aishwarya P S, Pranav Ajit Nair, Yashas Samaga B L, Toby James Boyd, Sanjiv Kumar, Prateek Jain, Praneeth Netrapalli

Transforming and Combining Rewards for Aligning Large Language Models
Zihao Wang, Chirag Nagpal, Jonathan Berant, Jacob Eisenstein, Alexander D'Amour, Sanmi Koyejo,
Victor Veitch

USTAD: Unified Single-Model Training Achieving Diverse Scores for Information Retrieval
Seungyeon Kim, Ankit Singh Rawat, Manzil Zaheer, Wittawat Jitkrittum, Veeranjaneyulu Sadhanala, Sadeep Jayasumana, Aditya Krishna Menon, Rob Fergus, Sanjiv Kumar

Adaptive Accompaniment with ReaLchords
Yusong Wu, Tim Cooijmans, Kyle Kastner, Adam Roberts, Ian Simon, Alexander Scarlatos, Chris Donahue, Cassie Tarakajian, Shayegan Omidshafiei*, Aaron Courville, Pablo Samuel Castro, Natasha Jaques, Cheng-Zhi Anna Huang

A Decoder-Only Foundation Model for Time-Series Forecasting (see blog post)
Abhimanyu Das, Weihao Kong, Rajat Sen, Yichen Zhou

Deep Fusion: Efficient Network Training via Pre-trained Initializations
Hanna Mazzawi, Javier Gonzalvo, Michael Wunder, Sammy Jerome, Benoit Dherin

Extracting Training Data from Document-Based VQA Models
Francesco Pinto, Nathalie, Rauschmayr, Florian Tramer, Philip Torr, Federico Tombari

FrameQuant: Flexible Low-Bit Quantization for Transformers
Harshavardhan Adepu, Zhanpeng Zeng, Li Zhang, Vikas Singh

H-Consistency Guarantees for Regression
Anqi Mao, Mehryar Mohri, Yutao Zhong

Implicit Bias of Policy Gradient in Linear Quadratic Control: Extrapolation to Unseen Initial States
Noam Razin, Yotam Alexander, Edo Cohen-Karlik, Raja Giryes, Amir Globerson, Nadav Cohen

Interpretability Illusions in the Generalization of Simplified Models
Dan Friedman*, Andrew Kyle Lampinen, Lucas Dixon, Danqi Chen, Asma Ghandeharioun

Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning
Sungwon Han*, Jinsung Yoon, Sercan O Arik, Tomas Pfister

MC-GTA: Metric-Constrained Model-Based Clustering Using Goodness-of-Fit Tests with Autocorrelations
Zhangyu Wang, Gengchen Mai, Krzysztof Janowicz, Ni Lao

Mean Estimation in the Add-Remove Model of Differential Privacy
Alex Kulesza, Ananda Suresh, Yuyan Wang

More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning
Kaiwen Wang, Owen Oertell, Alekh Agarwal, Nathan Kallus, Wen Sun

Online Learning with Bounded Recall
Jon Schneider, Kiran Vodrahalli

Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity
Lu Yin, You Wu, Zhenyu Zhang, Cheng-Yu Hsieh, Yaqing Wang, Yiling Jia, Gen Li, Ajay Kumar Jaiswal, Mykola Pechenizkiy, Yi Liang, Michael Bendersky, Zhangyang Wang, Shiwei Liu

Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelines
Yuchen Li, Alexandre Kirchmeyer, Aashay Mehta, Yilong Qin, Boris Dadachev, Kishore Papineni, Sanjiv Kumar, Andrej Risteski

SCoRe: Submodular Combinatorial Representation Learning
Anay Majee, Suraj Kothawade, Krishnateja Killamsetty, Rishabh K Iyer

Simplicity Bias via Global Convergence of Sharpness Minimization
Khashayar Gatmiry, Zhiyuan Li, Sashank J. Reddi, Stefanie Jegelka

Auto-Linear Phenomenon in Subsurface Imaging
Yinan Feng, Yinpeng Chen, Peng Jin, Shihang Feng, Youzuo Lin

FRAPPÉ: A Group Fairness Framework for Post-Processing Everything
Alexandru Tifrea*, Preethi Lahoti, Ben Packer, Yoni Halpern, Ahmad Beirami, Flavien Prost

Individualized Privacy Accounting via Subsampling with Applications in Combinatorial Optimization
Badih Ghazi, Pritish Kamath, Ravi Kumar, Pasin Manurangsi, Adam Sealfon

Online Speculative Decoding
Xiaoxuan Liu, Lanxiang Hu, Peter Bailis, Alvin Cheung, Zhijie Deng, Ion Stoica, Hao Zhang

The Pitfalls of Next-Token Prediction
Gregor Bachmann, Vaishnavh Nagarajan

PolySketchFormer: Fast Transformers via Sketching Polynomial Kernels
Praneeth Kacham, Vahab Mirrokni, Peilin Zhong

Position: Social Environment Design Should be Further Developed for AI-based Policy-Making
Edwin Zhang, Sadie Zhao, Tonghan Wang, Safwan Hossain, Henry Gasztowtt, Stephan Zheng, David C. Parkes, Milind Tambe, Yiling Chen

Prompt-Tuning Latent Diffusion Models for Inverse Problems
Hyungjin Chung, Jong Chul Ye, Peyman Milanfar, Mauricio Delbracio

VideoPrism: A Foundational Visual Encoder for Video Understanding (see blog post)
Long Zhao, Nitesh Bharadwaj Gundavarapu, Liangzhe Yuan, Hao Zhou, Shen Yan, Jennifer J. Sun, Luke Friedman, Rui Qian, Tobias Weyand, Yue Zhao*, Rachel Hornung, Florian Schroff, Ming-Hsuan Yang, David A Ross, Huisheng Wang, Hartwig Adam, Mikhail Sirotenko, Ting Liu, Boqing Gong

RLAIF vs. RLHF: Scaling Reinforcement Learning from Human Feedback with AI Feedback
Harrison Lee, Samrat Phatale, Hassan Mansoor, Thomas Mesnard, Johan Ferret, Kellie Ren Lu, Colton Bishop, Ethan Hall, Victor Carbune, Abhinav Rastogi, Sushant Prakash

From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers
Muhammed Emrullah Ildiz, Yixiao HUANG, Yingcong Li, Ankit Singh Rawat, Samet Oymak

Generalized Neural Collapse for a Large Number of Classes
Jiachen Jiang, Jinxin Zhou, Peng Wang, Qing Qu, Dustin G. Mixon, Chong You, Zhihui Zhu

High-Dimensional Geometric Streaming for Nearly Low Rank Data
Hossein Esfandiari, Praneeth Kacham, Vahab Mirrokni, David Woodruff, Peilin Zhong

Improved Communication-Privacy Trade-Offs in L2 Mean Estimation Under Streaming Differential Privacy
Wei-Ning Chen, Berivan Isik, Peter Kairouz, Albert No, Sewoong Oh, Zheng Xu

On Discrete Prompt Optimization for Diffusion Models
Ruochen Wang, Ting Liu, Cho-Jui Hsieh, Boqing Gong

OSSCAR: One-Shot Structured Pruning in Vision and Language Models with Combinatorial Optimization
Xiang Meng, Shibal Ibrahim, Kayhan Behdin, Hussein Hazimeh, Natalia Ponomareva, Rahul Mazumder

Weisfeiler-Leman at the Margin: When More Expressivity Matters
Billy Joe Franks, Christopher Morris, Ameya Velingker, Floris Geerts