166 citations · 595 across the 71 of their papers we have counts for
15 papers · 1 filter
Conformal Information Pursuit for Interactively Guiding Large Language Models
Kwan Ho Ryan Chan, Yuyan Ge, Edgar Dobriban +2
A significant use case of instruction-finetuned Large Language Models (LLMs) is to solve question-answering tasks interactively. In this setting, an LLM agent is tasked with making…
Synthetic-Powered Predictive Inference
Meshi Bashari, Roy Maor Lotan, Yonghoon Lee +2
Conformal prediction is a framework for predictive inference with a distribution-free, finite-sample guarantee. However, it tends to provide uninformative prediction sets when cali…
Jailbreaking Black Box Large Language Models in Twenty Queries
Patrick Chao, Alexander Robey, Edgar Dobriban +3
There is growing interest in ensuring that large language models (LLMs) align with human values. However, the alignment of such models is vulnerable to adversarial jailbreaks, whic…
PAC Prediction Sets for Meta-Learning
Sangdon Park, Edgar Dobriban, Insup Lee +1
Uncertainty quantification is a key component of machine learning models targeted at safety-critical systems such as in healthcare or autonomous vehicles. We study this problem in…
PAC-Wrap: Semi-Supervised PAC Anomaly Detection
Shuo Li, Xiayan Ji, Edgar Dobriban +2
Anomaly detection is essential for preventing hazardous outcomes for safety-critical applications like autonomous driving. Given their safety-criticality, these applications benefi…
Memory Classifiers: Two-stage Classification for Robustness in Machine Learning
Souradeep Dutta, Yahan Yang, Elena Bernardis +2
The performance of machine learning models can significantly degrade under distribution shifts of the data. We propose a new method for classification which can improve robustness…
Exploring with Sticky Mittens: Reinforcement Learning with Expert Interventions via Option Templates
Souradeep Dutta, Kaustubh Sridhar, Osbert Bastani +4
Long horizon robot learning tasks with sparse rewards pose a significant challenge for current reinforcement learning algorithms. A key feature enabling humans to learn challenging…
iDECODe: In-distribution Equivariance for Conformal Out-of-distribution Detection
Ramneet Kaur, Susmit Jha, Anirban Roy +4
Machine learning methods such as deep neural networks (DNNs), despite their success across different domains, are known to often generate incorrect predictions with high confidence…
Learning Augmentation Distributions using Transformed Risk Minimization
Evangelos Chatzipantazis, Stefanos Pertigkiozoglou, Kostas Daniilidis +1
We propose a new \emph{Transformed Risk Minimization} (TRM) framework as an extension of classical risk minimization. In TRM, we optimize not only over predictive models, but also…
Solon: Communication-efficient Byzantine-resilient Distributed Training via Redundant Gradients
Lingjiao Chen, Leshang Chen, Hongyi Wang +2
There has been a growing need to provide Byzantine-resilience in distributed model training. Existing robust distributed learning algorithms focus on developing sophisticated robus…
PAC Prediction Sets Under Covariate Shift
Sangdon Park, Edgar Dobriban, Insup Lee +1
An important challenge facing modern machine learning is how to rigorously quantify the uncertainty of model predictions. Conveying uncertainty is especially important when there a…
Understanding Generalization in Adversarial Training via the Bias-Variance Decomposition
Yaodong Yu, Zitong Yang, Edgar Dobriban +2
Adversarially trained models exhibit a large generalization gap: they can interpolate the training set even for large perturbation radii, but at the cost of large test error on cle…
DeltaGrad: Rapid retraining of machine learning models
Yinjun Wu, Edgar Dobriban, Susan B. Davidson
Machine learning models are not static and may need to be retrained on slightly changed datasets, for instance, with the addition or deletion of a set of data points. This has many…
Provable tradeoffs in adversarially robust classification
Edgar Dobriban, Hamed Hassani, David Hong +1
It is well known that machine learning methods can be vulnerable to adversarially-chosen perturbations of their inputs. Despite significant progress in the area, foundational open…
Implicit Regularization and Convergence for Weight Normalization
Xiaoxia Wu, Edgar Dobriban, Tongzheng Ren +5
Normalization methods such as batch [Ioffe and Szegedy, 2015], weight [Salimansand Kingma, 2016], instance [Ulyanov et al., 2016], and layer normalization [Baet al., 2016] have bee…