44 citations · 218 across the 42 of their papers we have counts for
13 papers · 1 filter
Test-Time Scaling Makes Overtraining Compute-Optimal
Nicholas Roberts, Sungjun Cho, Zhiqi Gao +7
Modern LLMs scale at test-time, e.g. via repeated sampling, where inference cost grows with model size and the number of samples. This creates a trade-off that pretraining scaling…
COSMOS: Predictable and Cost-Effective Adaptation of LLMs
Jiayu Wang, Aws Albarghouthi, Frederic Sala
Large language models (LLMs) achieve remarkable performance across numerous tasks by using a diverse array of adaptation strategies. However, optimally selecting a model and adapta…
Verified Training for Counterfactual Explanation Robustness under Data Shift
Anna P. Meyer, Yuhao Zhang, Aws Albarghouthi +1
Counterfactual explanations (CEs) enhance the interpretability of machine learning models by describing what changes to an input are necessary to change its prediction to a desired…
The Dataset Multiplicity Problem: How Unreliable Data Impacts Predictions
Anna P. Meyer, Aws Albarghouthi, Loris D'Antoni
We introduce dataset multiplicity, a way to study how inaccuracies, uncertainty, and social bias in training datasets impact test-time predictions. The dataset multiplicity framewo…
AutoWS-Bench-101: Benchmarking Automated Weak Supervision with 100 Labels
Nicholas Roberts, Xintong Li, Tzu-Heng Huang +7
Weak supervision (WS) is a powerful method to build labeled datasets for training supervised models in the face of little-to-no labeled data. It replaces hand-labeling data with ag…
Certifying Data-Bias Robustness in Linear Regression
Anna P. Meyer, Aws Albarghouthi, Loris D'Antoni
Datasets typically contain inaccuracies due to human error and societal biases, and these inaccuracies can affect the outcomes of models trained on such datasets. We present a tech…
BagFlip: A Certified Defense against Data Poisoning
Yuhao Zhang, Aws Albarghouthi, Loris D'Antoni
Machine learning models are vulnerable to data-poisoning attacks, in which an attacker maliciously modifies the training set to change the prediction of a learned model. In a trigg…
Certifying Robustness to Programmable Data Bias in Decision Trees
Anna P. Meyer, Aws Albarghouthi, Loris D'Antoni
Datasets can be biased due to societal inequities, human biases, under-representation of minorities, etc. Our goal is to certify that models produced by a learning algorithm are po…
Introduction to Neural Network Verification
Aws Albarghouthi
Deep learning has transformed the way we think of software and what it can do. But deep neural networks are fragile and their behaviors are often surprising. In many settings, we n…
Certified Robustness to Programmable Transformations in LSTMs
Yuhao Zhang, Aws Albarghouthi, Loris D'Antoni
Deep neural networks for natural language processing are fragile in the face of adversarial examples -- small input perturbations, like synonym substitution or word duplication, wh…
Interval Universal Approximation for Neural Networks
Zi Wang, Aws Albarghouthi, Gautam Prakriya +1
To verify safety and robustness of neural networks, researchers have successfully applied abstract interpretation, primarily using the interval abstract domain. In this paper, we s…
Backdoors in Neural Models of Source Code
Goutham Ramakrishnan, Aws Albarghouthi
Deep neural networks are vulnerable to a range of adversaries. A particularly pernicious class of vulnerabilities are backdoors, where model predictions diverge in the presence of…
Robustness to Programmable String Transformations via Augmented Abstract Training
Yuhao Zhang, Aws Albarghouthi, Loris D'Antoni
Deep neural networks for natural language processing tasks are vulnerable to adversarial input perturbations. In this paper, we present a versatile language for programmatically sp…