University of Pennsylvania

research

∙ 06/07/2022

NOMAD: Nonlinear Manifold Decoders for Operator Learning

Supervised learning in function spaces is an emerging area of machine le...

Jacob H. Seidman, et al. ∙

research

∙ 07/14/2021

Generative and reproducible benchmarks for comprehensive evaluation of machine learning classifiers

Understanding the strengths and weaknesses of machine learning (ML) algo...

Patryk Orzechowski, et al. ∙

research

∙ 10/28/2021

From Machine Learning to Robotics: Challenges and Opportunities for Embodied Intelligence

Machine learning has long since become a keystone technology, accelerati...

Nicholas Roy, et al. ∙

research

∙ 12/27/2019

Sample Complexity of Kalman Filtering for Unknown Systems

In this paper, we consider the task of designing a Kalman Filter (KF) fo...

Anastasios Tsiamis, et al. ∙

research

∙ 07/29/2021

Contemporary Symbolic Regression Methods and their Relative Performance

Many promising approaches to symbolic regression have been presented in ...

William La Cava, et al. ∙

research

∙ 01/30/2020

SGP-DT: Semantic Genetic Programming Based on Dynamic Targets

Semantic GP is a promising approach that introduces semantic awareness d...

Stefano Ruberto, et al. ∙

research

∙ 01/21/2020

EdgeNets:Edge Varying Graph Neural Networks

Driven by the outstanding performance of neural networks in the structur...

Elvin Isufi, et al. ∙

research

∙ 03/21/2019

Finite Sample Analysis of Stochastic System Identification

In this paper, we analyze the finite sample complexity of stochastic sys...

Anastasios Tsiamis, et al. ∙

research

∙ 12/29/2018

Monocular 3D Pose Recovery via Nonconvex Sparsity with Theoretical Analysis

For recovering 3D object poses from 2D images, a prevalent method is to ...

Jianqiao Wangni, et al. ∙

research

∙ 09/30/2019

Optimal Algorithms for Submodular Maximization with Distributed Constraints

We consider a class of discrete optimization problems that aim to maximi...

Alexander Robey, et al. ∙

research

∙ 05/02/2020

Obtaining Faithful Interpretations from Compositional Neural Networks

Neural module networks (NMNs) are a popular approach for modeling compos...

Sanjay Subramanian, et al. ∙

research

∙ 01/17/2022

Matrix Reordering for Noisy Disordered Matrices: Optimality and Computationally Efficient Algorithms

Motivated by applications in single-cell biology and metagenomics, we co...

T. Tony Cai, et al. ∙

research

∙ 04/18/2019

Continual Learning for Sentence Representations Using Conceptors

Distributed representations of sentences have become ubiquitous in natur...

Tianlin Liu, et al. ∙

research

∙ 10/11/2021

Graph Neural Network Guided Local Search for the Traveling Salesperson Problem

Solutions to the Traveling Salesperson Problem (TSP) have practical appl...

Benjamin Hudson, et al. ∙

research

∙ 06/09/2020

Foreshadowing the Benefits of Incidental Supervision

Learning theory mostly addresses the standard learning paradigm, assumin...

Hangfeng He, et al. ∙

research

∙ 04/28/2020

Genetic programming approaches to learning fair classifiers

Society has come to rely on algorithms like classifiers for important de...

William La Cava, et al. ∙

research

∙ 09/14/2021

Large-scale Autonomous Flight with Real-time Semantic SLAM under Dense Forest Canopy

In this letter, we propose an integrated autonomous flight and semantic ...

Xu Liu, et al. ∙

research

∙ 03/22/2022

Mixed Differential Privacy in Computer Vision

We introduce AdaMix, an adaptive differentially private algorithm for tr...

Aditya Golatkar, et al. ∙

research

∙ 09/05/2019

Minibatch Processing in Spiking Neural Networks

Spiking neural networks (SNNs) are a promising candidate for biologicall...

Daniel J. Saunders, et al. ∙

research

∙ 02/18/2020

Optimal Structured Principal Subspace Estimation: Metric Entropy and Minimax Rates

Driven by a wide range of applications, many principal subspace estimati...

T. Tony Cai, et al. ∙

research

∙ 12/03/2019

EventGAN: Leveraging Large Scale Image Datasets for Event Cameras

Event cameras provide a number of benefits over traditional cameras, suc...

Alex Zihao Zhu, et al. ∙

research

∙ 01/29/2020

Safe Predictors for Enforcing Input-Output Specifications

We present an approach for designing correct-by-construction neural netw...

Stephen Mell, et al. ∙

research

∙ 05/01/2020

TransOMCS: From Linguistic Graphs to Commonsense Knowledge

Commonsense knowledge acquisition is a key problem for artificial intell...

Hongming Zhang, et al. ∙

research

∙ 12/30/2021

Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks

Heterogeneous graph neural networks (HGNNs) have been blossoming in rece...

Qingsong Lv, et al. ∙

research

∙ 06/25/2022

Solution and Fitness Evolution (SAFE): Coevolving Solutions and Their Objective Functions

We recently highlighted a fundamental problem recognized to confound alg...

Moshe Sipper, et al. ∙

research

∙ 11/30/2020

Automating Artifact Detection in Video Games

In spite of advances in gaming hardware and software, gameplay is often ...

Parmida Davarmanesh, et al. ∙

research

∙ 07/28/2021

Goal-Oriented Script Construction

The knowledge of scripts, common chains of events in stereotypical scena...

Qing Lyu, et al. ∙

research

∙ 12/06/2018

Cross-Domain 3D Equivariant Image Embeddings

Spherical convolutional networks have been introduced recently as tools ...

Carlos Esteves, et al. ∙

research

∙ 04/01/2019

Equivariant Multi-View Networks

Several approaches to 3D vision tasks process multiple views of the inpu...

Carlos Esteves, et al. ∙

research

∙ 01/07/2020

An Exploration of Embodied Visual Exploration

Embodied computer vision considers perception for robots in general, uns...

Santhosh K. Ramakrishnan, et al. ∙

research

∙ 05/06/2021

Object-centric Video Prediction without Annotation

In order to interact with the world, agents must be able to predict the ...

Karl Schmeckpeper, et al. ∙

research

∙ 06/25/2022

Solution and Fitness Evolution (SAFE): A Study of Multiobjective Problems

We have recently presented SAFE – Solution And Fitness Evolution – a com...

Moshe Sipper, et al. ∙

research

∙ 01/08/2019

On the Capabilities and Limitations of Reasoning for Natural Language Understanding

Recent systems for natural language understanding are strong at overcomi...

Daniel Khashabi, et al. ∙

research

∙ 09/12/2019

Encoding High-Level Visual Attributes in Capsules for Explainable Medical Diagnoses

Deep neural networks are often called black-boxes due to their difficult...

Rodney LaLonde, et al. ∙

research

∙ 12/30/2019

Learning Predictive Models From Observation and Interaction

Learning predictive models from interaction with the world allows an age...

Karl Schmeckpeper, et al. ∙

research

∙ 12/21/2019

Depth Completion via Deep Basis Fitting

In this paper we consider the task of image-guided depth completion wher...

Chao Qu, et al. ∙

research

∙ 12/29/2019

Active Learning in Video Tracking

Active learning methods, like uncertainty sampling, combined with probab...

Sima Behpour, et al. ∙

research

∙ 02/17/2020

Causal Feature Discovery through Strategic Modification

We consider an online regression setting in which individuals adapt to t...

Yahav Bechavod, et al. ∙

research

∙ 06/18/2020

Spin-Weighted Spherical CNNs

Learning equivariant representations is a promising way to reduce sample...

Carlos Esteves, et al. ∙

research

∙ 12/28/2018

Predicting with Proxies

Predictive analytics is increasingly used to guide decision-making in ma...

Hamsa Bastani, et al. ∙

research

∙ 04/18/2019

Semantic variation operators for multidimensional genetic programming

Multidimensional genetic programming represents candidate solutions as s...

William La Cava, et al. ∙

research

∙ 12/17/2019

Cross-Lingual Ability of Multilingual BERT: An Empirical Study

Recent work has exhibited the surprising cross-lingual abilities of mult...

Karthikeyan K, et al. ∙

research

∙ 06/11/2020

Is deep learning necessary for simple classification tasks?

Automated machine learning (AutoML) and deep learning (DL) are two cutti...

Joseph D. Romano, et al. ∙

research

∙ 09/06/2019

A Baseline for Few-Shot Image Classification

Fine-tuning a deep network trained with the standard cross-entropy loss ...

Guneet S. Dhillon, et al. ∙

research

∙ 02/25/2022

Exploring with Sticky Mittens: Reinforcement Learning with Expert Interventions via Option Templates

Environments with sparse rewards and long horizons pose a significant ch...

Souradeep Dutta, et al. ∙

research

∙ 07/24/2022

CODiT: Conformal Out-of-Distribution Detection in Time-Series Data

Machine learning models are prone to making incorrect predictions on inp...

Ramneet Kaur, et al. ∙

research

∙ 01/07/2019

All Graphs Lead to Rome: Learning Geometric and Cycle-Consistent Representations with Graph Convolutional Networks

Image feature matching is a fundamental part of many geometric computer ...

Stephen Phillips, et al. ∙

research

∙ 11/10/2019

Not All Claims are Created Equal: Choosing the Right Approach to Assess Your Hypotheses

Empirical research in Natural Language Processing (NLP) has adopted a na...

Erfan Sadeqi Azer, et al. ∙

research

∙ 02/28/2022

Paper Plain: Making Medical Research Papers Approachable to Healthcare Consumers with Natural Language Processing

When seeking information not covered in patient-friendly documents, like...

Tal August, et al. ∙

research

∙ 10/02/2019

Distributed Attack-Robust Submodular Maximization for Multi-Robot Planning

We aim to guard swarm-robotics applications against denial-of-service (D...

Lifeng Zhou, et al. ∙

University of Pennsylvania

Featured Researchers