2 code implementations • NeurIPS 2013 • Richard Socher, Milind Ganjoo, Hamsa Sridhar, Osbert Bastani, Christopher D. Manning, Andrew Y. Ng
This work introduces a model that can recognize objects in images even if no training data is available for the objects.
1 code implementation • NeurIPS 2016 • Osbert Bastani, Yani Ioannou, Leonidas Lampropoulos, Dimitrios Vytiniotis, Aditya Nori, Antonio Criminisi
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.
1 code implementation • 5 Aug 2016 • Osbert Bastani, Rahul Sharma, Alex Aiken, Percy Liang
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
no code implementations • 23 May 2017 • Osbert Bastani, Carolyn Kim, Hamsa Bastani
Interpretability has become incredibly important as machine learning is increasingly used to inform consequential decisions.
no code implementations • 29 Jun 2017 • Osbert Bastani, Carolyn Kim, Hamsa Bastani
The ability to interpret machine learning models has become increasingly important now that machine learning is used to inform consequential decisions.
1 code implementation • NeurIPS 2018 • Osbert Bastani, Yewen Pu, Armando Solar-Lezama
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.
1 code implementation • 2 Dec 2018 • Osbert Bastani, Xin Zhang, Armando Solar-Lezama
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.
1 code implementation • 24 Jan 2019 • Min Wen, Osbert Bastani, Ufuk Topcu
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.
no code implementations • 24 Jan 2019 • Carolyn Kim, Osbert Bastani
We propose a framework for learning interpretable models from observational data that can be used to predict individual treatment effects (ITEs).
no code implementations • ICLR Workshop drlStructPred 2019 • Halley Young, Osbert Bastani, Mayur Naik
Significant strides have been made toward designing better generative models in recent years.
no code implementations • 24 Jan 2019 • Osbert Bastani
Reinforcement learning is a promising approach to learning robotics controllers.
1 code implementation • 25 May 2019 • Osbert Bastani
Reinforcement learning is a promising approach to synthesizing policies for challenging robotics tasks.
no code implementations • 24 Oct 2019 • Shuo Li, Osbert Bastani
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.
no code implementations • 25 Oct 2019 • Wenbo Zhang, Osbert Bastani, Vijay Kumar
Reinforcement learning is a promising approach to learning control policies for performing complex multi-agent robotics tasks.
Multi-agent Reinforcement Learning reinforcement-learning +1
no code implementations • 15 Nov 2019 • Himabindu Lakkaraju, Osbert Bastani
Our work is the first to empirically establish how user trust in black box models can be manipulated via misleading explanations.
1 code implementation • ICLR 2020 • Sangdon Park, Osbert Bastani, Nikolai Matni, Insup Lee
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.
no code implementations • 29 Feb 2020 • Sangdon Park, Osbert Bastani, James Weimer, Insup Lee
Our algorithm uses importance weighting to correct for the shift from the training to the real-world distribution.
no code implementations • ICLR 2020 • Jeevana Priya Inala, Osbert Bastani, Zenna Tavares, Armando Solar-Lezama
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.
1 code implementation • NeurIPS 2019 • Kishor Jothimurugan, Rajeev Alur, Osbert Bastani
Reinforcement learning is a promising approach for learning control policies for robot tasks.
no code implementations • 29 Oct 2020 • Kishor Jothimurugan, Osbert Bastani, Rajeev Alur
We propose a novel hierarchical reinforcement learning framework for control with continuous state and action spaces.
Hierarchical Reinforcement Learning reinforcement-learning +1
no code implementations • ICLR 2021 • Sangdon Park, Shuo Li, Insup Lee, Osbert Bastani
In our experiments, we demonstrate that our approach can be used to provide guarantees for state-of-the-art DNNs.
no code implementations • 12 Nov 2020 • Himabindu Lakkaraju, Nino Arsov, Osbert Bastani
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.
1 code implementation • NeurIPS 2021 • Alexis Ross, Himabindu Lakkaraju, Osbert Bastani
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.
1 code implementation • ICCV 2021 • Yecheng Jason Ma, Jeevana Priya Inala, Dinesh Jayaraman, Osbert Bastani
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.
no code implementations • 1 Jan 2021 • Halley Young, Maxwell Du, Osbert Bastani
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).
1 code implementation • NeurIPS 2020 • Jeevana Priya Inala, Yichen Yang, James Paulos, Yewen Pu, Osbert Bastani, Vijay Kumar, Martin Rinard, Armando Solar-Lezama
We study the problem of inferring communication structures that can solve cooperative multi-agent planning problems while minimizing the amount of communication.
1 code implementation • NeurIPS 2021 • Yichen David Yang, Jeevana Priya Inala, Osbert Bastani, Yewen Pu, Armando Solar-Lezama, Martin Rinard
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.
no code implementations • 18 Apr 2021 • Kan Xu, Xuanyi Zhao, Hamsa Bastani, Osbert Bastani
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.
1 code implementation • ICLR 2022 • Sangdon Park, Edgar Dobriban, Insup Lee, Osbert Bastani
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).
1 code implementation • NeurIPS 2021 • Kishor Jothimurugan, Suguman Bansal, Osbert Bastani, Rajeev Alur
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.
1 code implementation • NeurIPS 2021 • Yecheng Jason Ma, Dinesh Jayaraman, Osbert Bastani
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.
no code implementations • 19 Aug 2021 • Hamsa Bastani, Osbert Bastani, Wichinpong Park Sinchaisri
Workers spend a significant amount of time learning how to make good decisions.
no code implementations • 22 Sep 2021 • Kan Xu, Hamsa Bastani, Osbert Bastani
We study this problem from the perspective of the statistical concept of parameter identification.
no code implementations • 29 Sep 2021 • Sooyong Jang, Sangdon Park, Insup Lee, Osbert Bastani
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.
no code implementations • NeurIPS Workshop AIPLANS 2021 • Osbert Bastani
We study the problem of synthesizing programs that include machine learning components such as deep neural networks (DNNs).
no code implementations • NeurIPS Workshop AIPLANS 2021 • Stephen Mell, Favyen Bastani, Stephan Zdancewic, Osbert Bastani
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.
no code implementations • 11 Oct 2021 • Osbert Bastani
We study the problem of synthesizing programs that include machine learning components such as deep neural networks (DNNs).
1 code implementation • 25 Oct 2021 • Wanqiao Xu, Jason Yecheng Ma, Kan Xu, Hamsa Bastani, Osbert Bastani
A key challenge to deploying reinforcement learning in practice is avoiding excessive (harmful) exploration in individual episodes.
1 code implementation • 14 Dec 2021 • Yecheng Jason Ma, Andrew Shen, Osbert Bastani, Dinesh Jayaraman
Further, CAP adaptively tunes this penalty during training using true cost feedback from the environment.
2 code implementations • 4 Feb 2022 • Yecheng Jason Ma, Andrew Shen, Dinesh Jayaraman, Osbert Bastani
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.
no code implementations • 20 Feb 2022 • Soham Dan, Osbert Bastani, Dan Roth
Currently, deep neural networks struggle to generalize robustly to such shifts in the data distribution.
1 code implementation • 25 Feb 2022 • Souradeep Dutta, Kaustubh Sridhar, Osbert Bastani, Edgar Dobriban, James Weimer, Insup Lee, Julia Parish-Morris
We formulate expert intervention as allowing the agent to execute option templates before learning an implementation.
no code implementations • 15 Apr 2022 • Shuo Li, Sangdon Park, Xiayan Ji, Insup Lee, Osbert Bastani
Accurately detecting and tracking multi-objects is important for safety-critical applications such as autonomous navigation.
1 code implementation • ACL 2022 • George Tolkachev, Stephen Mell, Steve Zdancewic, Osbert Bastani
A key challenge facing natural language interfaces is enabling users to understand the capabilities of the underlying system.
1 code implementation • 2 Jun 2022 • Osbert Bastani, Varun Gupta, Christopher Jung, Georgy Noarov, Ramya Ramalingam, Aaron Roth
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.
no code implementations • 6 Jun 2022 • Kishor Jothimurugan, Suguman Bansal, Osbert Bastani, Rajeev Alur
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.
1 code implementation • 7 Jun 2022 • Yecheng Jason Ma, Jason Yan, Dinesh Jayaraman, Osbert Bastani
Offline goal-conditioned reinforcement learning (GCRL) promises general-purpose skill learning in the form of reaching diverse goals from purely offline datasets.
no code implementations • 6 Jul 2022 • Sangdon Park, Edgar Dobriban, Insup Lee, Osbert Bastani
Uncertainty quantification is a key component of machine learning models targeted at safety-critical systems such as in healthcare or autonomous vehicles.
1 code implementation • 30 Sep 2022 • Yecheng Jason Ma, Shagun Sodhani, Dinesh Jayaraman, Osbert Bastani, Vikash Kumar, Amy Zhang
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.
no code implementations • 11 Nov 2022 • Vashist Avadhanula, Omar Abdul Baki, Hamsa Bastani, Osbert Bastani, Caner Gocmen, Daniel Haimovich, Darren Hwang, Dima Karamshuk, Thomas Leeper, Jiayuan Ma, Gregory Macnamara, Jake Mullett, Christopher Palow, Sung Park, Varun S Rajagopal, Kevin Schaeffer, Parikshit Shah, Deeksha Sinha, Nicolas Stier-Moses, Peng Xu
We describe the current content moderation strategy employed by Meta to remove policy-violating content from its platforms.
no code implementations • 15 Nov 2022 • Tsai-Hsuan Chung, Vahid Rostami, Hamsa Bastani, Osbert Bastani
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.
1 code implementation • 17 Nov 2022 • Sangdon Park, Osbert Bastani, Taesoo Kim
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.
1 code implementation • CVPR 2023 • Wenwen Si, Shuo Li, Sangdon Park, Insup Lee, Osbert Bastani
Experiments demonstrate the efficacy of the partial-covering patch in solving the complex bounding box problem.
no code implementations • 3 Feb 2023 • Kavi Gupta, Osbert Bastani, Armando Solar-Lezama
Real-world processes often contain intermediate state that can be modeled as an extremely sparse tensor.
1 code implementation • 6 Feb 2023 • Kishor Jothimurugan, Steve Hsu, Osbert Bastani, Rajeev Alur
We formulate the problem as a two agent zero-sum game in which the adversary picks the sequence of subtasks.
2 code implementations • 15 Feb 2023 • Alexander Shypula, Aman Madaan, Yimeng Zeng, Uri Alon, Jacob Gardner, Milad Hashemi, Graham Neubig, Parthasarathy Ranganathan, Osbert Bastani, Amir Yazdanbakhsh
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.
1 code implementation • 17 Feb 2023 • Adam Khakhar, Stephen Mell, Osbert Bastani
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.
no code implementations • 22 May 2023 • Yecheng Jason Ma, Kausik Sivakumar, Jason Yan, Osbert Bastani, Dinesh Jayaraman
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.
no code implementations • 25 May 2023 • Natalie Maus, Yimeng Zeng, Daniel Allen Anderson, Phillip Maffettone, Aaron Solomon, Peyton Greenside, Osbert Bastani, Jacob R. Gardner
Furthermore, it is challenging to adapt pure generative approaches to other settings, e. g., when constraints exist.
no code implementations • 26 May 2023 • Rajeev Alur, Osbert Bastani, Kishor Jothimurugan, Mateo Perez, Fabio Somenzi, Ashutosh Trivedi
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).
1 code implementation • 1 Jun 2023 • Yecheng Jason Ma, William Liang, Vaidehi Som, Vikash Kumar, Amy Zhang, Osbert Bastani, Dinesh Jayaraman
We present Language-Image Value learning (LIV), a unified objective for vision-language representation and reward learning from action-free videos with text annotations.
1 code implementation • 7 Jul 2023 • Shuo Li, Sangdon Park, Insup Lee, Osbert Bastani
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.
no code implementations • 5 Oct 2023 • Haosen Ge, Hamsa Bastani, Osbert Bastani
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.
no code implementations • 12 Oct 2023 • Zichen Zhang, Yunshuang Li, Osbert Bastani, Abhishek Gupta, Dinesh Jayaraman, Yecheng Jason Ma, Luca Weihs
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.
1 code implementation • 19 Oct 2023 • Wenwen Si, Sangdon Park, Insup Lee, Edgar Dobriban, Osbert Bastani
We propose a novel algorithm for constructing prediction sets with PAC guarantees in the label shift setting.
1 code implementation • 19 Oct 2023 • Yecheng Jason Ma, William Liang, Guanzhi Wang, De-An Huang, Osbert Bastani, Dinesh Jayaraman, Yuke Zhu, Linxi Fan, Anima Anandkumar
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.
1 code implementation • 9 Feb 2024 • Michael S. Yao, Yimeng Zeng, Hamsa Bastani, Jacob Gardner, James C. Gee, Osbert Bastani
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.
no code implementations • 4 Apr 2024 • Xinmeng Huang, Shuo Li, Mengxin Yu, Matteo Sesia, Hamed Hassani, Insup Lee, Osbert Bastani, Edgar Dobriban
Language Models (LMs) have shown promising performance in natural language generation.
1 code implementation • ICML 2020 • Jiani Huang, Calvin Smith, Osbert Bastani, Rishabh Singh, Aws Albarghouthi, Mayur Naik
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.
no code implementations • ICML 2020 • Himabindu Lakkaraju, Nino Arsov, Osbert Bastani
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.
no code implementations • Findings (EMNLP) 2021 • Soham Dan, Osbert Bastani, Dan Roth
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.