158 citations · 280 across the 27 of their papers we have counts for
14 papers · 1 filter
Reliable Gradient-free and Likelihood-free Prompt Tuning
Maohao Shen, Soumya Ghosh, Prasanna Sattigeri +3
Due to privacy or commercial constraints, large pre-trained language models (PLMs) are often offered as black-box APIs. Fine-tuning such models to downstream tasks is challenging b…
Label-Free Concept Bottleneck Models
Tuomas Oikarinen, Subhro Das, Lam M. Nguyen +1
Concept bottleneck models (CBM) are a popular way of creating more interpretable neural networks by having hidden layer neurons correspond to human-understandable concepts. However…
Variance-reduced Clipping for Non-convex Optimization
Amirhossein Reisizadeh, Haochuan Li, Subhro Das +1
Gradient clipping is a standard training technique used in deep learning applications such as large-scale language modeling to mitigate exploding gradients. Recent experimental stu…
Group Fairness with Uncertainty in Sensitive Attributes
Abhin Shah, Maohao Shen, Jongha Jon Ryu +4
Learning a fair predictive model is crucial to mitigate biased decisions against minority groups in high-stakes applications. A common approach to learn such a model involves solvi…
ConCerNet: A Contrastive Learning Based Framework for Automated Conservation Law Discovery and Trustworthy Dynamical System Prediction
Wang Zhang, Tsui-Wei Weng, Subhro Das +3
Deep neural networks (DNN) have shown great capacity of modeling a dynamical system; nevertheless, they usually do not obey physics constraints such as conservation laws. This pape…
Who Should Predict? Exact Algorithms For Learning to Defer to Humans
Hussein Mozannar, Hunter Lang, Dennis Wei +3
Automated AI classifiers should be able to defer the prediction to a human decision maker to ensure more accurate predictions. In this work, we jointly train a classifier with a re…
Post-hoc Uncertainty Learning using a Dirichlet Meta-Model
Maohao Shen, Yuheng Bu, Prasanna Sattigeri +3
It is known that neural networks have the problem of being over-confident when directly using the output label distribution to generate uncertainty measures. Existing methods mainl…
Attacking c-MARL More Effectively: A Data Driven Approach
Nhan H. Pham, Lam M. Nguyen, Jie Chen +3
In recent years, a proliferation of methods were developed for cooperative multi-agent reinforcement learning (c-MARL). However, the robustness of c-MARL agents against adversarial…
Selective Regression Under Fairness Criteria
Abhin Shah, Yuheng Bu, Joshua Ka-Wing Lee +4
Selective regression allows abstention from prediction if the confidence to make an accurate prediction is not sufficient. In general, by allowing a reject option, one expects the…
GAT-GMM: Generative Adversarial Training for Gaussian Mixture Models
Farzan Farnia, William Wang, Subhro Das +1
Generative adversarial networks (GANs) learn the distribution of observed samples through a zero-sum game between two machine players, a generator and a discriminator. While GANs a…
A Dynamical Systems Approach for Convergence of the Bayesian EM Algorithm
Orlando Romero, Subhro Das, Pin-Yu Chen +1
Out of the recent advances in systems and control (S\&C)-based analysis of optimization algorithms, not enough work has been specifically dedicated to machine learning (ML) algorit…
Model adaptation and unsupervised learning with non-stationary batch data under smooth concept drift
Subhro Das, Prasanth Lade, Soundar Srinivasan
Most predictive models assume that training and test data are generated from a stationary process. However, this assumption does not hold true in practice. In this paper, we consid…
Learning Patient Engagement in Care Management: Performance vs. Interpretability
Subhro Das, Chandramouli Maduri, Ching-Hua Chen +1
The health outcomes of high-need patients can be substantially influenced by the degree of patient engagement in their own care. The role of care managers includes that of enrollin…
Interpretable Subgroup Discovery in Treatment Effect Estimation with Application to Opioid Prescribing Guidelines
Chirag Nagpal, Dennis Wei, Bhanukiran Vinzamuri +4
The dearth of prescribing guidelines for physicians is one key driver of the current opioid epidemic in the United States. In this work, we analyze medical and pharmaceutical claim…