Search Results for author:
Found 71 papers, 35 papers with code
Zero-Shot Learning Through Cross-Modal Transfer
This work introduces a model that can recognize objects in images even if no training data is available for the objects.
Measuring Neural Net Robustness with Constraints
Despite having high accuracy, neural nets have been shown to be susceptible to adversarial examples, where a small perturbation to an input can cause it to become mislabeled.
Synthesizing Program Input Grammars
We present an algorithm for synthesizing a context-free grammar encoding the language of valid program inputs from a set of input examples and blackbox access to the program.
Programming Languages
Interpreting Blackbox Models via Model Extraction
Interpretability has become incredibly important as machine learning is increasingly used to inform consequential decisions.
Interpretability via Model Extraction
The ability to interpret machine learning models has become increasingly important now that machine learning is used to inform consequential decisions.
Verifiable Reinforcement Learning via Policy Extraction
While deep reinforcement learning has successfully solved many challenging control tasks, its real-world applicability has been limited by the inability to ensure the safety of learned policies.
Probabilistic Verification of Fairness Properties via Concentration
As machine learning systems are increasingly used to make real world legal and financial decisions, it is of paramount importance that we develop algorithms to verify that these systems do not discriminate against minorities.
Algorithms for Fairness in Sequential Decision Making
It has recently been shown that if feedback effects of decisions are ignored, then imposing fairness constraints such as demographic parity or equality of opportunity can actually exacerbate unfairness.
Learning Interpretable Models with Causal Guarantees
We propose a framework for learning interpretable models from observational data that can be used to predict individual treatment effects (ITEs).
Learning Neurosymbolic Generative Models via Program Synthesis
Significant strides have been made toward designing better generative models in recent years.
Sample Complexity of Estimating the Policy Gradient for Nearly Deterministic Dynamical Systems
Reinforcement learning is a promising approach to learning robotics controllers.
Safe Reinforcement Learning with Nonlinear Dynamics via Model Predictive Shielding
Reinforcement learning is a promising approach to synthesizing policies for challenging robotics tasks.
Robust Model Predictive Shielding for Safe Reinforcement Learning with Stochastic Dynamics
We build on the idea of model predictive shielding (MPS), where a backup controller is used to override the learned policy as needed to ensure safety.
MAMPS: Safe Multi-Agent Reinforcement Learning via Model Predictive Shielding
Reinforcement learning is a promising approach to learning control policies for performing complex multi-agent robotics tasks.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
"How do I fool you?": Manipulating User Trust via Misleading Black Box Explanations
Our work is the first to empirically establish how user trust in black box models can be manipulated via misleading explanations.
PAC Confidence Sets for Deep Neural Networks via Calibrated Prediction
We propose an algorithm combining calibrated prediction and generalization bounds from learning theory to construct confidence sets for deep neural networks with PAC guarantees---i. e., the confidence set for a given input contains the true label with high probability.
Calibrated Prediction with Covariate Shift via Unsupervised Domain Adaptation
Our algorithm uses importance weighting to correct for the shift from the training to the real-world distribution.
Synthesizing Programmatic Policies that Inductively Generalize
We show that our algorithm can be used to learn policies that inductively generalize to novel environments, whereas traditional neural network policies fail to do so.
A Composable Specification Language for Reinforcement Learning Tasks
Reinforcement learning is a promising approach for learning control policies for robot tasks.
Abstract Value Iteration for Hierarchical Reinforcement Learning
We propose a novel hierarchical reinforcement learning framework for control with continuous state and action spaces.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
PAC Confidence Predictions for Deep Neural Network Classifiers
In our experiments, we demonstrate that our approach can be used to provide guarantees for state-of-the-art DNNs.
Robust and Stable Black Box Explanations
To the best of our knowledge, this work makes the first attempt at generating post hoc explanations that are robust to a general class of adversarial perturbations that are of practical interest.
Learning Models for Actionable Recourse
As machine learning models are increasingly deployed in high-stakes domains such as legal and financial decision-making, there has been growing interest in post-hoc methods for generating counterfactual explanations.
Likelihood-Based Diverse Sampling for Trajectory Forecasting
We propose Likelihood-Based Diverse Sampling (LDS), a method for improving the quality and the diversity of trajectory samples from a pre-trained flow model.
Neurosymbolic Deep Generative Models for Sequence Data with Relational Constraints
We propose a novel approach for incorporating structure in the form of relational constraints between different subcomponents of an example (e. g., lines of a poem or measures of music).
Neurosymbolic Transformers for Multi-Agent Communication
We study the problem of inferring communication structures that can solve cooperative multi-agent planning problems while minimizing the amount of communication.
Program Synthesis Guided Reinforcement Learning for Partially Observed Environments
Our results demonstrate that our approach can obtain the benefits of program-guided reinforcement learning without requiring the user to provide a new guiding program for every new task.
Group-Sparse Matrix Factorization for Transfer Learning of Word Embeddings
However, learning word embeddings from new domains with limited training data can be challenging, because the meaning/usage may be different in the new domain, e. g., the word ``positive'' typically has positive sentiment, but often has negative sentiment in medical notes since it may imply that a patient tested positive for a disease.
PAC Prediction Sets Under Covariate Shift
Our approach focuses on the setting where there is a covariate shift from the source distribution (where we have labeled training examples) to the target distribution (for which we want to quantify uncertainty).
Compositional Reinforcement Learning from Logical Specifications
Our approach then incorporates reinforcement learning to learn neural network policies for each edge (sub-task) within a Dijkstra-style planning algorithm to compute a high-level plan in the graph.
Conservative Offline Distributional Reinforcement Learning
We prove that CODAC learns a conservative return distribution -- in particular, for finite MDPs, CODAC converges to an uniform lower bound on the quantiles of the return distribution; our proof relies on a novel analysis of the distributional Bellman operator.
Improving Human Sequential Decision-Making with Reinforcement Learning
Workers spend a significant amount of time learning how to make good decisions.
Robust Generalization of Quadratic Neural Networks via Function Identification
We study this problem from the perspective of the statistical concept of parameter identification.
Sequential Covariate Shift Detection Using Classifier Two-Sample Tests
This problem can naturally be solved using a two-sample test--- i. e., test whether the current test distribution of covariates equals the training distribution of covariates.
PAC Synthesis of Machine Learning Programs
We study the problem of synthesizing programs that include machine learning components such as deep neural networks (DNNs).
Synthesizing Video Trajectory Queries
A key challenge is that queries are difficult for end users to develop: queries must reason about complex spatial and temporal patterns in object trajectories in order to select trajectories of interest, and predicates often include real-valued parameters (e. g., whether two cars are within a certain distance) that can be tedious to manually tune.
Synthesizing Machine Learning Programs with PAC Guarantees via Statistical Sketching
We study the problem of synthesizing programs that include machine learning components such as deep neural networks (DNNs).
Uniformly Conservative Exploration in Reinforcement Learning
A key challenge to deploying reinforcement learning in practice is avoiding excessive (harmful) exploration in individual episodes.
Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning
Further, CAP adaptively tunes this penalty during training using true cost feedback from the environment.
Versatile Offline Imitation from Observations and Examples via Regularized State-Occupancy Matching
We propose State Matching Offline DIstribution Correction Estimation (SMODICE), a novel and versatile regression-based offline imitation learning (IL) algorithm derived via state-occupancy matching.
Understanding Robust Generalization in Learning Regular Languages
Currently, deep neural networks struggle to generalize robustly to such shifts in the data distribution.
Exploring with Sticky Mittens: Reinforcement Learning with Expert Interventions via Option Templates
We formulate expert intervention as allowing the agent to execute option templates before learning an implementation.
Towards PAC Multi-Object Detection and Tracking
Accurately detecting and tracking multi-objects is important for safety-critical applications such as autonomous navigation.
Counterfactual Explanations for Natural Language Interfaces
A key challenge facing natural language interfaces is enabling users to understand the capabilities of the underlying system.
Practical Adversarial Multivalid Conformal Prediction
It is computationally lightweight -- comparable to split conformal prediction -- but does not require having a held-out validation set, and so all data can be used for training models from which to derive a conformal score.
Specification-Guided Learning of Nash Equilibria with High Social Welfare
Our empirical evaluation demonstrates that our algorithm computes equilibrium policies with high social welfare, whereas state-of-the-art baselines either fail to compute Nash equilibria or compute ones with comparatively lower social welfare.
How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression
Offline goal-conditioned reinforcement learning (GCRL) promises general-purpose skill learning in the form of reaching diverse goals from purely offline datasets.
PAC Prediction Sets for Meta-Learning
Uncertainty quantification is a key component of machine learning models targeted at safety-critical systems such as in healthcare or autonomous vehicles.
VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training
Given the inherent cost and scarcity of in-domain, task-specific robot data, learning from large, diverse, offline human videos has emerged as a promising path towards acquiring a generally useful visual representation for control; however, how these human videos can be used for general-purpose reward learning remains an open question.
Bandits for Online Calibration: An Application to Content Moderation on Social Media Platforms
We describe the current content moderation strategy employed by Meta to remove policy-violating content from its platforms.
Decision-Aware Learning for Optimizing Health Supply Chains
We apply our framework to optimize the distribution of essential medicines in collaboration with policymakers in Sierra Leone; highly uncertain demand and limited budgets currently result in excessive unmet demand.
ACon$^2$: Adaptive Conformal Consensus for Provable Blockchain Oracles
To address the oracle problem, we propose an adaptive conformal consensus (ACon$^2$) algorithm that derives a consensus set of data from multiple oracle contracts via the recent advance in online uncertainty quantification learning.
Angelic Patches for Improving Third-Party Object Detector Performance
Experiments demonstrate the efficacy of the partial-covering patch in solving the complex bounding box problem.
SPARLING: Learning Latent Representations with Extremely Sparse Activations
Real-world processes often contain intermediate state that can be modeled as an extremely sparse tensor.
Robust Subtask Learning for Compositional Generalization
We formulate the problem as a two agent zero-sum game in which the adversary picks the sequence of subtasks.
Learning Performance-Improving Code Edits
Next, we propose a broad range of adaptation strategies for code optimization; for prompting, these include retrieval-based few-shot prompting and chain-of-thought, and for finetuning, these include performance-conditioned generation and synthetic data augmentation based on self-play.
PAC Prediction Sets for Large Language Models of Code
Given a trained code generation model, our algorithm leverages a programming language's abstract syntax tree to generate a set of programs such that the correct program is in the set with high-confidence.
TOM: Learning Policy-Aware Models for Model-Based Reinforcement Learning via Transition Occupancy Matching
Standard model-based reinforcement learning (MBRL) approaches fit a transition model of the environment to all past experience, but this wastes model capacity on data that is irrelevant for policy improvement.
Inverse Protein Folding Using Deep Bayesian Optimization
Furthermore, it is challenging to adapt pure generative approaches to other settings, e. g., when constraints exist.
Policy Synthesis and Reinforcement Learning for Discounted LTL
The difficulty of manually specifying reward functions has led to an interest in using linear temporal logic (LTL) to express objectives for reinforcement learning (RL).
LIV: Language-Image Representations and Rewards for Robotic Control
We present Language-Image Value learning (LIV), a unified objective for vision-language representation and reward learning from action-free videos with text annotations.
TRAQ: Trustworthy Retrieval Augmented Question Answering via Conformal Prediction
To address this challenge, we propose the Trustworthy Retrieval Augmented Question Answering, or $\textit{TRAQ}$, which provides the first end-to-end statistical correctness guarantee for RAG.
Rethinking Fairness for Human-AI Collaboration
However, we show that it may be infeasible to design algorithmic recommendations that are simultaneously fair in isolation, compliance-robustly fair, and more accurate than the human policy; thus, if our goal is to improve the equity and accuracy of human-AI collaboration, it may not be desirable to enforce traditional fairness constraints.
Universal Visual Decomposer: Long-Horizon Manipulation Made Easy
Learning long-horizon manipulation tasks, however, is a long-standing challenge, and demands decomposing the overarching task into several manageable subtasks to facilitate policy learning and generalization to unseen tasks.
PAC Prediction Sets Under Label Shift
We propose a novel algorithm for constructing prediction sets with PAC guarantees in the label shift setting.
Eureka: Human-Level Reward Design via Coding Large Language Models
The generality of Eureka also enables a new gradient-free in-context learning approach to reinforcement learning from human feedback (RLHF), readily incorporating human inputs to improve the quality and the safety of the generated rewards without model updating.
Generative Adversarial Bayesian Optimization for Surrogate Objectives
To address this limitation, we propose generative adversarial Bayesian optimization (GABO) using adaptive source critic regularization, a task-agnostic framework for Bayesian optimization that employs a Lipschitz-bounded source critic model to constrain the optimization trajectory to regions where the surrogate function is reliable.
Uncertainty in Language Models: Assessment through Rank-Calibration
Language Models (LMs) have shown promising performance in natural language generation.
Generating Programmatic Referring Expressions via Program Synthesis
The policy neural network employs a program interpreter that provides immediate feedback on the consequences of the decisions made by the policy, and also takes into account the uncertainty in the symbolic representation of the image.
Robust Black Box Explanations Under Distribution Shift
As machine learning black boxes are increasingly being deployed in real-world applications, there has been a growing interest in developing post hoc explanations that summarize the behaviors of these black box models.
Few-Shot Novel Concept Learning for Semantic Parsing
This way the concept learning problem is naturally a program synthesis problem and our algorithm learns from a few examples to synthesize a program representing the novel concept.
