18 citations · 20 across the 19 of their papers we have counts for
21 papers
SEVerA: Verified Synthesis of Self-Evolving Agents
Debangshu Banerjee, Changming Xu, Eugene Ie +5
Recent advances have shown the effectiveness of self-evolving LLM agents on tasks such as program repair and scientific discovery. In this paradigm, a planner LLM synthesizes an ag…
DafnyPro: LLM-Assisted Automated Verification for Dafny Programs
Debangshu Banerjee, Olivier Bouissou, Stefan Zetzsche
We present DafnyPro, an inference-time framework that enhances LLMs for generating verification annotations in Dafny. DafnyPro comprises three key components: a diff-checker that p…
BEAVER: An Efficient Deterministic LLM Verifier
Tarun Suresh, Nalin Wadhwa, Debangshu Banerjee +1
As large language models (LLMs) transition from research prototypes to production systems, practitioners often need reliable methods to verify model outputs and characterize tail r…
Why DPO is a Misspecified Estimator and How to Fix It
Aditya Gopalan, Sayak Ray Chowdhury, Debangshu Banerjee
Direct alignment algorithms such as Direct Preference Optimization (DPO) fine-tune models based on preference data, using only supervised learning instead of two-stage reinforcemen…
Evolving Abstract Transformers for Gradient-Guided, Adaptable Abstract Interpretation
Shaurya Gomber, Debangshu Banerjee, Gagandeep Singh
Current numerical abstract interpretation relies on fixed, hand-crafted, instruction-specific transformers tailored to each domain, causing three key limitations: transformers cann…
Data Shifts Hurt CoT: A Theoretical Study
Lang Yin, Debangshu Banerjee, Gagandeep Singh
Chain of Thought (CoT) has been applied to various large language models (LLMs) and proven to be effective in improving the quality of outputs. In recent studies, transformers are…
DINGO: Constrained Inference for Diffusion LLMs
Tarun Suresh, Debangshu Banerjee, Shubham Ugare +2
Diffusion LLMs have emerged as a promising alternative to conventional autoregressive LLMs, offering significant potential for improved runtime efficiency. However, existing diffus…
Support is All You Need for Certified VAE Training
Changming Xu, Debangshu Banerjee, Deepak Vasisht +1
Variational Autoencoders (VAEs) have become increasingly popular and deployed in safety-critical applications. In such applications, we want to give certified probabilistic guarant…
CRANE: Reasoning with constrained LLM generation
Debangshu Banerjee, Tarun Suresh, Shubham Ugare +2
Code generation, symbolic math reasoning, and other tasks require LLMs to produce outputs that are both syntactically and semantically correct. Constrained LLM generation is a prom…
Risk-Aware Alignment Must Incorporate Reward Uncertainty
Debangshu Banerjee, Aditya Gopalan, Kintan Saha
We consider the problem of policy optimization with noisy rewards, where the policy is constrained to be in the neighborhood of a reference policy.We study the risk of the policy o…
Relational DNN Verification With Cross Executional Bound Refinement
Debangshu Banerjee, Gagandeep Singh
We focus on verifying relational properties defined over deep neural networks (DNNs) such as robustness against universal adversarial perturbations (UAP), certified worst-case hamm…
Bad Values but Good Behavior: Learning Highly Misspecified Bandits and MDPs
Debangshu Banerjee, Aditya Gopalan
Parametric, feature-based reward models are employed by a variety of algorithms in decision-making settings such as bandits and Markov decision processes (MDPs). The typical assump…
Incremental Randomized Smoothing Certification
Shubham Ugare, Tarun Suresh, Debangshu Banerjee +2
Randomized smoothing-based certification is an effective approach for obtaining robustness certificates of deep neural networks (DNNs) against adversarial attacks. This method cons…
Incremental Verification of Neural Networks
Shubham Ugare, Debangshu Banerjee, Sasa Misailovic +1
Complete verification of deep neural networks (DNNs) can exactly determine whether the DNN satisfies a desired trustworthy property (e.g., robustness, fairness) on an infinite set…
Interpreting Robustness Proofs of Deep Neural Networks
Debangshu Banerjee, Avaljot Singh, Gagandeep Singh
In recent years numerous methods have been developed to formally verify the robustness of deep neural networks (DNNs). Though the proposed techniques are effective in providing mat…
On the Minimax Regret for Linear Bandits in a wide variety of Action Spaces
Debangshu Banerjee, Aditya Gopalan
As noted in the works of \cite{lattimore2020bandit}, it has been mentioned that it is an open problem to characterize the minimax regret of linear bandits in a wide variety of acti…
Markov Chain Concentration with an Application in Reinforcement Learning
Debangshu Banerjee
Given random variables whose joint distribution is given as we will use the Martingale Method to show any Lipshitz Function over these random variables is…
Exploration in Linear Bandits with Rich Action Sets and its Implications for Inference
Debangshu Banerjee, Avishek Ghosh, Sayak Ray Chowdhury +1
We present a non-asymptotic lower bound on the eigenspectrum of the design matrix generated by any linear bandit algorithm with sub-linear regret when the action set has well-behav…
Critic Algorithms using Cooperative Networks
Debangshu Banerjee, Kavita Wagh
An algorithm is proposed for policy evaluation in Markov Decision Processes which gives good empirical results with respect to convergence rates. The algorithm tracks the Projected…
HEX and Neurodynamic Programming
Debangshu Banerjee
Hex is a complex game with a high branching factor. For the first time Hex is being attempted to be solved without the use of game tree structures and associated methods of pruning…
Vertex Guarding for Dynamic Orthogonal Art Galleries
Debangshu Banerjee, R. Inkulu
We devise an algorithm for surveying a dynamic orthogonal polygonal domain by placing one guard at each vertex in a subset of its vertices, i.e., whenever an orthogonal polygonal d…