94 citations · 449 across the 53 of their papers we have counts for
24 papers · 1 filter
Resource-efficient Inference with Foundation Model Programs
Lunyiu Nie, Zhimin Ding, Kevin Yu +3
The inference-time resource costs of large language and vision models present a growing challenge in production deployments. We propose the use of foundation model programs, i.e.,…
Canopy: Property-Driven Learning for Congestion Control
Chenxi Yang, Divyanshu Saxena, Rohit Dwivedula +3
Learning-based congestion controllers offer better adaptability compared to traditional heuristics. However, the unreliability of learning techniques can cause learning-based contr…
Symbolic Regression with a Learned Concept Library
Arya Grayeli, Atharva Sehgal, Omar Costilla-Reyes +2
We present a novel method for symbolic regression (SR), the task of searching for compact programmatic hypotheses that best explain a dataset. The problem is commonly solved using…
Prompt Tuning Strikes Back: Customizing Foundation Models with Low-Rank Prompt Adaptation
Abhinav Jain, Swarat Chaudhuri, Thomas Reps +1
Parameter-Efficient Fine-Tuning (PEFT) has become the standard for customising Foundation Models (FMs) to user-specific downstream tasks. However, typical PEFT methods require stor…
LTL-Constrained Policy Optimization with Cycle Experience Replay
Ameesh Shah, Cameron Voloshin, Chenxi Yang +3
Linear Temporal Logic (LTL) offers a precise means for constraining the behavior of reinforcement learning agents. However, in many settings where both satisfaction and optimality…
Online Cascade Learning for Efficient Inference over Streams
Lunyiu Nie, Zhimin Ding, Erdong Hu +2
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 suc…
Neurosymbolic Grounding for Compositional World Models
Atharva Sehgal, Arya Grayeli, Jennifer J. Sun +1
We introduce Cosmos, a framework for object-centric world modeling that is designed for compositional generalization (CompGen), i.e., high performance on unseen input scenes obtain…
Automata Learning from Preference and Equivalence Queries
Eric Hsiung, Joydeep Biswas, Swarat Chaudhuri
Active automata learning from membership and equivalence queries is a foundational problem with numerous applications. We propose a novel variant of the active automata learning pr…
A Probabilistic Framework for Modular Continual Learning
Lazar Valkov, Akash Srivastava, Swarat Chaudhuri +1
Modular approaches that use a different composition of modules for each problem are a promising direction in continual learning (CL). However, searching through the large, discrete…
Certifiably Robust Reinforcement Learning through Model-Based Abstract Interpretation
Chenxi Yang, Greg Anderson, Swarat Chaudhuri
We present a reinforcement learning (RL) framework in which the learned policy comes with a machine-checkable certificate of provable adversarial robustness. Our approach, called C…
Guiding Safe Exploration with Weakest Preconditions
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. We present…
Policy Optimization with Linear Temporal Logic Constraints
Cameron Voloshin, Hoang M. Le, Swarat Chaudhuri +1
We study the problem of policy optimization (PO) with linear temporal logic (LTL) constraints. The language of LTL allows flexible description of tasks that may be unnatural to enc…
Safe Neurosymbolic Learning with Differentiable Symbolic Execution
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. Such neurosymbolic programs arise in many…
Neural Program Generation Modulo Static Analysis
Rohan Mukherjee, Yeming Wen, Dipak Chaudhari +3
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 th…
Unsupervised Learning of Neurosymbolic Encoders
Eric Zhan, Jennifer J. Sun, Ann Kennedy +2
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-specif…
Interpreting Expert Annotation Differences in Animal Behavior
Megan Tjandrasuwita, Jennifer J. Sun, Ann Kennedy +2
Hand-annotated data can vary due to factors such as subjective differences, intra-rater variability, and differing annotator expertise. We study annotations from different experts…
Neurosymbolic Reinforcement Learning with Formally Verified Exploration
Greg Anderson, Abhinav Verma, Isil Dillig +1
We present Revel, a partially neural reinforcement learning (RL) framework for provably safe exploration in continuous state and action spaces. A key challenge for provably safe de…
Learning Differentiable Programs with Admissible Neural Heuristics
Ameesh Shah, Eric Zhan, Jennifer J. Sun +3
We study the problem of learning differentiable functions expressed as programs in a domain-specific language. Such programmatic models can offer benefits such as composability and…
Meta-Meta Classification for One-Shot Learning
Arkabandhu Chowdhury, Dipak Chaudhari, Swarat Chaudhuri +1
We present a new approach, called meta-meta classification, to learning in small-data settings. In this approach, one uses a large set of learning problems to design an ensemble of…
Imitation-Projected Programmatic Reinforcement Learning
Abhinav Verma, Hoang M. Le, Yisong Yue +1
We study the problem of programmatic reinforcement learning, in which policies are represented as short programs in a symbolic language. Programmatic policies can be more interpret…
Control Regularization for Reduced Variance Reinforcement Learning
Richard Cheng, Abhinav Verma, Gabor Orosz +3
Dealing with high variance is a significant challenge in model-free reinforcement learning (RL). Existing methods are unreliable, exhibiting high variance in performance from run t…
Representing Formal Languages: A Comparison Between Finite Automata and Recurrent Neural Networks
Joshua J. Michalenko, Ameesh Shah, Abhinav Verma +3
We investigate the internal representations that a recurrent neural network (RNN) uses while learning to recognize a regular formal language. Specifically, we train a RNN on positi…
Programmatically Interpretable Reinforcement Learning
Abhinav Verma, Vijayaraghavan Murali, Rishabh Singh +2
We present a reinforcement learning framework, called Programmatically Interpretable Reinforcement Learning (PIRL), that is designed to generate interpretable and verifiable agent…
HOUDINI: Lifelong Learning as Program Synthesis
Lazar Valkov, Dipak Chaudhari, Akash Srivastava +2
We present a neurosymbolic framework for the lifelong learning of algorithmic tasks that mix perception and procedural reasoning. Reusing high-level concepts across domains and lea…