Search Results for author: Swarat Chaudhuri

Found 37 papers, 14 papers with code

Deep Policy Optimization with Temporal Logic Constraints

no code implementations17 Apr 2024 Ameesh Shah, Cameron Voloshin, Chenxi Yang, Abhinav Verma, Swarat Chaudhuri, Sanjit A. Seshia

In our work, we consider the setting where the task is specified by an LTL objective and there is an additional scalar reward that we need to optimize.

Reinforcement Learning (RL)

Grounding Data Science Code Generation with Input-Output Specifications

no code implementations12 Feb 2024 Yeming Wen, Pengcheng Yin, Kensen Shi, Henryk Michalewski, Swarat Chaudhuri, Alex Polozov

Specifically, we propose GIFT4Code, a novel approach for the instruction fine-tuning of LLMs with respect to I/O specifications.

Code Generation

Online Cascade Learning for Efficient Inference over Streams

no code implementations7 Feb 2024 Lunyiu Nie, Zhimin Ding, Erdong Hu, Christopher Jermaine, Swarat Chaudhuri

Large Language Models (LLMs) have a natural role in answering complex queries about data streams, but the high computational cost of LLM inference makes them infeasible in many such tasks.

Imitation Learning

Batched Low-Rank Adaptation of Foundation Models

no code implementations9 Dec 2023 Yeming Wen, Swarat Chaudhuri

Low-Rank Adaptation (LoRA) has recently gained attention for fine-tuning foundation models by incorporating trainable low-rank matrices, thereby reducing the number of trainable parameters.

Code Generation speech-recognition +1

MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning

1 code implementation24 Oct 2023 Zayne Sprague, Xi Ye, Kaj Bostrom, Swarat Chaudhuri, Greg Durrett

We evaluate a range of LLMs and prompting techniques on this dataset and characterize the gaps that remain for techniques like chain-of-thought to perform robust reasoning.

Neurosymbolic Grounding for Compositional World Models

no code implementations19 Oct 2023 Atharva Sehgal, Arya Grayeli, Jennifer J. Sun, Swarat Chaudhuri

We introduce Cosmos, a framework for object-centric world modeling that is designed for compositional generalization (CG), i. e., high performance on unseen input scenes obtained through the composition of known visual "atoms."

Learning Reward Machines through Preference Queries over Sequences

no code implementations18 Aug 2023 Eric Hsiung, Joydeep Biswas, Swarat Chaudhuri

Reward machines have shown great promise at capturing non-Markovian reward functions for learning tasks that involve complex action sequencing.

Deductive Additivity for Planning of Natural Language Proofs

1 code implementation5 Jul 2023 Zayne Sprague, Kaj Bostrom, Swarat Chaudhuri, Greg Durrett

Specifically, we evaluate whether embedding spaces exhibit a property we call deductive additivity: the sum of premise statement embeddings should be close to embeddings of conclusions based on those premises.

Language Modelling Large Language Model +1

A Probabilistic Framework for Modular Continual Learning

no code implementations11 Jun 2023 Lazar Valkov, Akash Srivastava, Swarat Chaudhuri, Charles Sutton

To address this challenge, we develop a modular CL framework, called PICLE, that accelerates search by using a probabilistic model to cheaply compute the fitness of each composition.

Continual Learning

Coarse-Tuning Models of Code with Reinforcement Learning Feedback

no code implementations25 May 2023 Abhinav Jain, Chima Adiole, Swarat Chaudhuri, Thomas Reps, Chris Jermaine

Our experiments show that RLCF raises the odds that an LLM-generated program compiles, is executable, and produces the right output on tests, often allowing LLMs to match the performance of 2x-8x larger LLMs.

Program Synthesis reinforcement-learning

Certifiably Robust Reinforcement Learning through Model-Based Abstract Interpretation

no code implementations26 Jan 2023 Chenxi Yang, Greg Anderson, Swarat Chaudhuri

In each learning iteration, it uses the current version of this model and an external abstract interpreter to construct a differentiable signal for provable robustness.

Adversarial Robustness reinforcement-learning +1

Natural Language Deduction with Incomplete Information

2 code implementations1 Nov 2022 Zayne Sprague, Kaj Bostrom, Swarat Chaudhuri, Greg Durrett

A growing body of work studies how to answer a question or verify a claim by generating a natural language "proof": a chain of deductive inferences yielding the answer based on a set of premises.

Text Generation

Neurosymbolic Programming for Science

no code implementations10 Oct 2022 Jennifer J. Sun, Megan Tjandrasuwita, Atharva Sehgal, Armando Solar-Lezama, Swarat Chaudhuri, Yisong Yue, Omar Costilla-Reyes

Neurosymbolic Programming (NP) techniques have the potential to accelerate scientific discovery.

Guiding Safe Exploration with Weakest Preconditions

no code implementations28 Sep 2022 Greg Anderson, Swarat Chaudhuri, Isil Dillig

In reinforcement learning for safety-critical settings, it is often desirable for the agent to obey safety constraints at all points in time, including during training.

Continuous Control reinforcement-learning +2

Policy Optimization with Linear Temporal Logic Constraints

no code implementations20 Jun 2022 Cameron Voloshin, Hoang M. Le, Swarat Chaudhuri, Yisong Yue

We study the problem of policy optimization (PO) with linear temporal logic (LTL) constraints.

Safe Neurosymbolic Learning with Differentiable Symbolic Execution

2 code implementations NeurIPS Workshop AIPLANS 2021 Chenxi Yang, Swarat Chaudhuri

We study the problem of learning worst-case-safe parameters for programs that use neural networks as well as symbolic, human-written code.

Natural Language Deduction through Search over Statement Compositions

no code implementations16 Jan 2022 Kaj Bostrom, Zayne Sprague, Swarat Chaudhuri, Greg Durrett

In settings from fact-checking to question answering, we frequently want to know whether a collection of evidence (premises) entails a hypothesis.

Fact Checking Question Answering

Neural Program Generation Modulo Static Analysis

no code implementations NeurIPS 2021 Rohan Mukherjee, Yeming Wen, Dipak Chaudhari, Thomas W. Reps, Swarat Chaudhuri, Chris Jermaine

State-of-the-art neural models of source code tend to be evaluated on the generation of individual expressions and lines of code, and commonly fail on long-horizon tasks such as the generation of entire method bodies.

Unsupervised Learning of Neurosymbolic Encoders

1 code implementation28 Jul 2021 Eric Zhan, Jennifer J. Sun, Ann Kennedy, Yisong Yue, Swarat Chaudhuri

We present a framework for the unsupervised learning of neurosymbolic encoders, which are encoders obtained by composing neural networks with symbolic programs from a domain-specific language.

Program Synthesis Sports Analytics

Interpreting Expert Annotation Differences in Animal Behavior

no code implementations11 Jun 2021 Megan Tjandrasuwita, Jennifer J. Sun, Ann Kennedy, Swarat Chaudhuri, Yisong Yue

Hand-annotated data can vary due to factors such as subjective differences, intra-rater variability, and differing annotator expertise.

Program Synthesis

Flexible Generation of Natural Language Deductions

1 code implementation EMNLP 2021 Kaj Bostrom, Xinyu Zhao, Swarat Chaudhuri, Greg Durrett

Natural language is an attractive representation for this purpose -- it is both highly expressive and easy for humans to understand.


Neurosymbolic Reinforcement Learning with Formally Verified Exploration

1 code implementation NeurIPS 2020 Greg Anderson, Abhinav Verma, Isil Dillig, Swarat Chaudhuri

We present Revel, a partially neural reinforcement learning (RL) framework for provably safe exploration in continuous state and action spaces.

reinforcement-learning Reinforcement Learning (RL) +1

Learning Differentiable Programs with Admissible Neural Heuristics

1 code implementation NeurIPS 2020 Ameesh Shah, Eric Zhan, Jennifer J. Sun, Abhinav Verma, Yisong Yue, Swarat Chaudhuri

This relaxed program is differentiable and can be trained end-to-end, and the resulting training loss is an approximately admissible heuristic that can guide the combinatorial search.

Imitation-Projected Programmatic Reinforcement Learning

no code implementations NeurIPS 2019 Abhinav Verma, Hoang M. Le, Yisong Yue, Swarat Chaudhuri

First, we view our learning task as optimization in policy space, modulo the constraint that the desired policy has a programmatic representation, and solve this optimization problem using a form of mirror descent that takes a gradient step into the unconstrained policy space and then projects back onto the constrained space.

Continuous Control Imitation Learning +3

Control Regularization for Reduced Variance Reinforcement Learning

1 code implementation14 May 2019 Richard Cheng, Abhinav Verma, Gabor Orosz, Swarat Chaudhuri, Yisong Yue, Joel W. Burdick

We show that functional regularization yields a bias-variance trade-off, and propose an adaptive tuning strategy to optimize this trade-off.

Continuous Control reinforcement-learning +1

Finite Automata Can be Linearly Decoded from Language-Recognizing RNNs

no code implementations ICLR 2019 Joshua J. Michalenko, Ameesh Shah, Abhinav Verma, Swarat Chaudhuri, Ankit B. Patel

We study the internal representations that a recurrent neural network (RNN) uses while learning to recognize a regular formal language.


Optimization and Abstraction: A Synergistic Approach for Analyzing Neural Network Robustness

no code implementations22 Apr 2019 Greg Anderson, Shankara Pailoor, Isil Dillig, Swarat Chaudhuri

In recent years, the notion of local robustness (or robustness for short) has emerged as a desirable property of deep neural networks.

Representing Formal Languages: A Comparison Between Finite Automata and Recurrent Neural Networks

no code implementations27 Feb 2019 Joshua J. Michalenko, Ameesh Shah, Abhinav Verma, Richard G. Baraniuk, Swarat Chaudhuri, Ankit B. Patel

We investigate the internal representations that a recurrent neural network (RNN) uses while learning to recognize a regular formal language.


Programmatically Interpretable Reinforcement Learning

no code implementations ICML 2018 Abhinav Verma, Vijayaraghavan Murali, Rishabh Singh, Pushmeet Kohli, Swarat Chaudhuri

Unlike the popular Deep Reinforcement Learning (DRL) paradigm, which represents policies by neural networks, PIRL represents policies using a high-level, domain-specific programming language.

Car Racing reinforcement-learning +1

HOUDINI: Lifelong Learning as Program Synthesis

2 code implementations NeurIPS 2018 Lazar Valkov, Dipak Chaudhari, Akash Srivastava, Charles Sutton, Swarat Chaudhuri

We present a neurosymbolic framework for the lifelong learning of algorithmic tasks that mix perception and procedural reasoning.

Program Synthesis Transfer Learning

Bounded Policy Synthesis for POMDPs with Safe-Reachability Objectives

no code implementations29 Jan 2018 Yue Wang, Swarat Chaudhuri, Lydia E. Kavraki

In this work, we study POMDPs with safe-reachability objectives, which require that with a probability above some threshold, a goal state is eventually reached while keeping the probability of visiting unsafe states below some threshold.


Neural Attribute Machines for Program Generation

no code implementations25 May 2017 Matthew Amodio, Swarat Chaudhuri, Thomas W. Reps

During generation, NAMs make significantly fewer violations of the constraints of the underlying grammar than RNNs trained only on samples from the language of the grammar.


Neural Sketch Learning for Conditional Program Generation

1 code implementation ICLR 2018 Vijayaraghavan Murali, Letao Qi, Swarat Chaudhuri, Chris Jermaine

We study the problem of generating source code in a strongly typed, Java-like programming language, given a label (for example a set of API calls or types) carrying a small amount of information about the code that is desired.

Cannot find the paper you are looking for? You can Submit a new open access paper.