2.4k citations · 12.3k across the 115 of their papers we have counts for
43 papers · 1 filter
Benchmark Datasets for Lead-Lag Forecasting on Social Platforms
Kimia Kazemian, Zhenzhen Liu, Yangfanyu Yang +9
Social and collaborative platforms emit multivariate time-series traces in which early interactions -- such as views, likes, or downloads -- are followed, sometimes months or years…
Rethinking LLM Unlearning Objectives: A Gradient Perspective and Go Beyond
Qizhou Wang, Jin Peng Zhou, Zhanke Zhou +3
Large language models (LLMs) should undergo rigorous audits to identify potential risks, such as copyright and privacy infringements. Once these risks emerge, timely updates are cr…
Graders should cheat: privileged information enables expert-level automated evaluations
Jin Peng Zhou, Sébastien M. R. Arnold, Nan Ding +3
Auto-evaluating language models (LMs), i.e., using a grader LM to evaluate the candidate LM, is an appealing way to accelerate the evaluation process and the cost associated with i…
: Provably Optimal Distributional RL for LLM Post-Training
Jin Peng Zhou, Kaiwen Wang, Jonathan Chang +5
Reinforcement learning (RL) post-training is crucial for LLM alignment and reasoning, but existing policy-based methods, such as PPO and DPO, can fall short of fixing shortcuts inh…
PhantomWiki: On-Demand Datasets for Reasoning and Retrieval Evaluation
Albert Gong, Kamilė Stankevičiūtė, Chao Wan +6
High-quality benchmarks are essential for evaluating reasoning and retrieval capabilities of large language models (LLMs). However, curating datasets for this purpose is not a perm…
Online Feature Updates Improve Online (Generalized) Label Shift Adaptation
Ruihan Wu, Siddhartha Datta, Yi Su +3
This paper addresses the prevalent issue of label shift in an online setting with missing labels, where data distributions change over time and obtaining timely labels is challengi…
Detecting Out-of-Distribution Objects through Class-Conditioned Inpainting
Quang-Huy Nguyen, Jin Peng Zhou, Zhenzhen Liu +4
Recent object detectors have achieved impressive accuracy in identifying objects seen during training. However, real-world deployment often introduces novel and unexpected objects,…
Learning to Invert: Simple Adaptive Attacks for Gradient Inversion in Federated Learning
Ruihan Wu, Xiangyu Chen, Chuan Guo +1
Gradient inversion attack enables recovery of training samples from model gradients in federated learning (FL), and constitutes a serious threat to data privacy. To mitigate this v…
Does Label Differential Privacy Prevent Label Inference Attacks?
Ruihan Wu, Jin Peng Zhou, Kilian Q. Weinberger +1
Label differential privacy (label-DP) is a popular framework for training private ML models on datasets with public features and sensitive private labels. Despite its rigorous priv…
Is High Variance Unavoidable in RL? A Case Study in Continuous Control
Johan Bjorck, Carla P. Gomes, Kilian Q. Weinberger
Reinforcement learning (RL) experiments have notoriously high variance, and minor details can have disproportionately large effects on measured outcomes. This is problematic for cr…
Online Adaptation to Label Distribution Shift
Ruihan Wu, Chuan Guo, Yi Su +1
Machine learning models often encounter distribution shifts when deployed in the real world. In this paper, we focus on adaptation to label distribution shift in the online setting…
Towards Deeper Deep Reinforcement Learning with Spectral Normalization
Johan Bjorck, Carla P. Gomes, Kilian Q. Weinberger
In computer vision and natural language processing, innovations in model architecture that increase model capacity have reliably translated into gains in performance. In stark cont…
Low-Precision Reinforcement Learning: Running Soft Actor-Critic in Half Precision
Johan Bjorck, Xiangyu Chen, Christopher De Sa +2
Low-precision training has become a popular approach to reduce compute requirements, memory footprint, and energy consumption in supervised learning. In contrast, this promising ap…
Understanding Decoupled and Early Weight Decay
Johan Bjorck, Kilian Weinberger, Carla Gomes
Weight decay (WD) is a traditional regularization technique in deep learning, but despite its ubiquity, its behavior is still an area of active research. Golatkar et al. have recen…
Revisiting Meta-Learning as Supervised Learning
Wei-Lun Chao, Han-Jia Ye, De-Chuan Zhan +2
Recent years have witnessed an abundance of new publications and approaches on meta-learning. This community-wide enthusiasm has sparked great insights but has also created a pleth…
On Feature Normalization and Data Augmentation
Boyi Li, Felix Wu, Ser-Nam Lim +2
The moments (a.k.a., mean and standard deviation) of latent features are often removed as noise when training image recognition models, to increase stability and reduce training ti…
On Hiding Neural Networks Inside Neural Networks
Chuan Guo, Ruihan Wu, Kilian Q. Weinberger
Modern neural networks often contain significantly more parameters than the size of their training data. We show that this excess capacity provides an opportunity for embedding sec…
Convolutional Networks with Dense Connectivity
Gao Huang, Zhuang Liu, Geoff Pleiss +2
Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the…
Identifying Mislabeled Data using the Area Under the Margin Ranking
Geoff Pleiss, Tianyi Zhang, Ethan R. Elenberg +1
Not all data in a typical training set help with generalization; some samples can be overly ambiguous or outrightly mislabeled. This paper introduces a new method to identify such…
A New Defense Against Adversarial Images: Turning a Weakness into a Strength
Tao Yu, Shengyuan Hu, Chuan Guo +2
Natural images are virtually surrounded by low-density misclassified regions that can be efficiently discovered by gradient-guided search --- enabling the generation of adversarial…
Simple Black-box Adversarial Attacks
Chuan Guo, Jacob R. Gardner, Yurong You +2
We propose an intriguingly simple method for the construction of adversarial images in the black-box setting. In constrast to the white-box scenario, constructing black-box adversa…
Exact Gaussian Processes on a Million Data Points
Ke Alexander Wang, Geoff Pleiss, Jacob R. Gardner +3
Gaussian processes (GPs) are flexible non-parametric models, with a capacity that grows with the available data. However, computational constraints with standard inference procedur…
Simplifying Graph Convolutional Networks
Felix Wu, Tianyi Zhang, Amauri Holanda de Souza +3
Graph Convolutional Networks (GCNs) and their variants have experienced significant attention and have become the de facto methods for learning graph representations. GCNs derive i…
Gradient Regularized Budgeted Boosting
Zhixiang Eddie Xu, Matt J. Kusner, Kilian Q. Weinberger +1
As machine learning transitions increasingly towards real world applications controlling the test-time cost of algorithms becomes more and more crucial. Recent work, such as the Gr…