6 papers
TCS-BENCH: Benchmarking State-of-the-Art Generative AI Theoretical Computer Science Research Ability
Vincent Cohen-Addad, Dimitris Paparas, Ernest van Wijland +13
We introduce TCS-Bench, a benchmark for evaluating Large Language Models (LLMs) on research-level Theoretical Computer Science (TCS) proof generation. TCS-Bench consists of theorem…
Phantoms and Disclosures: A Statistical Framework for Auditing Privacy in Synthetic Data
Kareem Amin, Rudrajit Das, Alessandro Epasto +4
The rapid adoption of generative AI and Large Language Models (LLMs) has spurred interest in synthetic data as a privacy-preserving alternative to sensitive real-world datasets. Ho…
Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting
Sunny Sanyal, Hayden Prairie, Rudrajit Das +2
Fine-tuning a pre-trained model on a downstream task often degrades its original capabilities, a phenomenon known as "catastrophic forgetting". This is especially an issue when one…
Understanding the Training Speedup from Sampling with Approximate Losses
Rudrajit Das, Xi Chen, Bertram Ieong +2
It is well known that selecting samples with large losses/gradients can significantly reduce the number of training steps. However, the selection overhead is often too high to yiel…
Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing
Adel Javanmard, Rudrajit Das, Alessandro Epasto +1
Retraining a model using its own predictions together with the original, potentially noisy labels is a well-known strategy for improving the model performance. While prior works ha…
Retraining with Predicted Hard Labels Provably Increases Model Accuracy
Rudrajit Das, Inderjit S. Dhillon, Alessandro Epasto +5
The performance of a model trained with noisy labels is often improved by simply \textit{retraining} the model with its \textit{own predicted hard labels} (i.e., 1/0 labels). Yet,…