290 citations · 1.9k across the 78 of their papers we have counts for
82 papers
Learning Regions of Interest for Bayesian Optimization with Adaptive Level-Set Estimation
Fengxue Zhang, Jialin Song, James Bowden +4
We study Bayesian optimization (BO) in high-dimensional and non-stationary scenarios. Existing algorithms for such scenarios typically require extensive hyperparameter tuning, whic…
Conformal Generative Modeling on Triangulated Surfaces
Victor Dorobantu, Charlotte Borcherds, Yisong Yue
We propose conformal generative modeling, a framework for generative modeling on 2D surfaces approximated by discrete triangle meshes. Our approach leverages advances in discrete c…
Eventual Discounting Temporal Logic Counterfactual Experience Replay
Cameron Voloshin, Abhinav Verma, Yisong Yue
Linear temporal logic (LTL) offers a simplified way of specifying tasks for policy optimization that may otherwise be difficult to describe with scalar reward functions. However, t…
BKinD-3D: Self-Supervised 3D Keypoint Discovery from Multi-View Videos
Jennifer J. Sun, Lili Karashchuk, Amil Dravid +9
Quantifying motion in 3D is important for studying the behavior of humans and other animals, but manual pose annotations are expensive and time-consuming to obtain. Self-supervised…
Self-Supervised Keypoint Discovery in Behavioral Videos
Jennifer J. Sun, Serim Ryou, Roni Goldshmid +6
We propose a method for learning the posture and structure of agents from unlabelled behavioral videos. Starting from the observation that behaving agents are generally the main so…
Automatic Synthesis of Diverse Weak Supervision Sources for Behavior Analysis
Albert Tseng, Jennifer J. Sun, Yisong Yue
Obtaining annotations for large training sets is expensive, especially in settings where domain knowledge is required, such as behavior analysis. Weak supervision has been studied…
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…
Learning Pseudo-Backdoors for Mixed Integer Programs
Aaron Ferber, Jialin Song, Bistra Dilkina +1
We propose a machine learning approach for quickly solving Mixed Integer Programs (MIP) by learning to prioritize a set of decision variables, which we call pseudo-backdoors, for b…
The Multi-Agent Behavior Dataset: Mouse Dyadic Social Interactions
Jennifer J. Sun, Tomomi Karigo, Dipam Chakraborty +8
Multi-agent behavior modeling aims to understand the interactions that occur between agents. We present a multi-agent dataset from behavioral neuroscience, the Caltech Mouse Social…
Computing the Information Content of Trained Neural Networks
Jeremy Bernstein, Yisong Yue
How much information does a learning algorithm extract from the training data and store in a neural network's weights? Too much, and the network would overfit to the training data.…
Learning by Turning: Neural Architecture Aware Optimisation
Yang Liu, Jeremy Bernstein, Markus Meister +1
Descent methods for deep networks are notoriously capricious: they require careful tuning of step size, momentum and weight decay, and which method will work best on a new benchmar…
Disentangling Observed Causal Effects from Latent Confounders using Method of Moments
Anqi Liu, Hao Liu, Tongxin Li +3
Discovering the complete set of causal relations among a group of variables is a challenging unsupervised learning problem. Often, this challenge is compounded by the fact that the…
Architecture Agnostic Neural Networks
Sabera Talukder, Guruprasad Raghavan, Yisong Yue
In this paper, we explore an alternate method for synthesizing neural network architectures, inspired by the brain's stochastic synaptic pruning. During a person's lifetime, numero…
Neural-Swarm2: Planning and Control of Heterogeneous Multirotor Swarms using Learned Interactions
Guanya Shi, Wolfgang Hönig, Xichen Shi +2
We present Neural-Swarm2, a learning-based method for motion planning and control that allows heterogeneous multirotors in a swarm to safely fly in close proximity. Such operation…
On the Benefits of Early Fusion in Multimodal Representation Learning
George Barnum, Sabera Talukder, Yisong Yue
Intelligently reasoning about the world often requires integrating data from multiple modalities, as any individual modality may contain unreliable or incomplete information. Prior…
Machine Learning Based Path Planning for Improved Rover Navigation (Pre-Print Version)
Neil Abcouwer, Shreyansh Daftry, Siddarth Venkatraman +6
Enhanced AutoNav (ENav), the baseline surface navigation software for NASA's Perseverance rover, sorts a list of candidate paths for the rover to traverse, then uses the Approximat…
Task Programming: Learning Data Efficient Behavior Representations
Jennifer J. Sun, Ann Kennedy, Eric Zhan +3
Specialized domain knowledge is often necessary to accurately annotate training sets for in-depth analysis, but can be burdensome and time-consuming to acquire from domain experts.…
Towards Robust Data-Driven Control Synthesis for Nonlinear Systems with Actuation Uncertainty
Andrew J. Taylor, Victor D. Dorobantu, Sarah Dean +3
Modern nonlinear control theory seeks to endow systems with properties such as stability and safety, and has been deployed successfully across various domains. Despite this success…
ROIAL: Region of Interest Active Learning for Characterizing Exoskeleton Gait Preference Landscapes
Kejun Li, Maegan Tucker, Erdem Bıyık +6
Characterizing what types of exoskeleton gaits are comfortable for users, and understanding the science of walking more generally, require recovering a user's utility landscape. Le…
Competitive Control with Delayed Imperfect Information
Chenkai Yu, Guanya Shi, Soon-Jo Chung +2
This paper studies the impact of imperfect information in online control with adversarial disturbances. In particular, we consider both delayed state feedback and inexact predictio…
Iterative Amortized Policy Optimization
Joseph Marino, Alexandre Piché, Alessandro Davide Ialongo +1
Policy networks are a central feature of deep reinforcement learning (RL) algorithms for continuous control, enabling the estimation and sampling of high-value actions. From the va…
Graph Neural Networks for the Prediction of Substrate-Specific Organic Reaction Conditions
Serim Ryou, Michael R. Maser, Alexander Y. Cui +3
We present a systematic investigation using graph neural networks (GNNs) to model organic chemical reactions. To do so, we prepared a dataset collection of four ubiquitous reaction…
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…
Active Learning under Label Shift
Eric Zhao, Anqi Liu, Animashree Anandkumar +1
We address the problem of active learning under label shift: when the class proportions of source and target domains differ. We introduce a "medial distribution" to incorporate a t…