56 citations · 243 across the 35 of their papers we have counts for
40 papers
Distribution Guided Active Feature Acquisition
Yang Li, Junier Oliva
Human agents routinely reason on instances with incomplete and muddied data (and weigh the cost of obtaining further features). In contrast, much of ML is devoted to the unrealisti…
Towards Cost Sensitive Decision Making
Yang Li, Junier Oliva
Many real-world situations allow for the acquisition of additional relevant information when making decisions with limited or uncertain data. However, traditional RL approaches eit…
Phoneme Hallucinator: One-shot Voice Conversion via Set Expansion
Siyuan Shan, Yang Li, Amartya Banerjee +1
Voice conversion (VC) aims at altering a person's voice to make it sound similar to the voice of another person while preserving linguistic content. Existing methods suffer from a…
Anomaly Detection via Gumbel Noise Score Matching
Ahsan Mahmood, Junier Oliva, Martin Styner
We propose Gumbel Noise Score Matching (GNSM), a novel unsupervised method to detect anomalies in categorical data. GNSM accomplishes this by estimating the scores, i.e. the gradie…
Acquisition Conditioned Oracle for Nongreedy Active Feature Acquisition
Michael Valancius, Max Lennon, Junier Oliva
We develop novel methodology for active feature acquisition (AFA), the study of how to sequentially acquire a dynamic (on a per instance basis) subset of features that minimizes ac…
Deeply-Learned Generalized Linear Models with Missing Data
David K Lim, Naim U Rashid, Junier B Oliva +1
Deep Learning (DL) methods have dramatically increased in popularity in recent years, with significant growth in their application to supervised learning problems in the biomedical…
Distribution-based Sketching of Single-Cell Samples
Vishal Athreya Baskaran, Jolene Ranek, Siyuan Shan +2
Modern high-throughput single-cell immune profiling technologies, such as flow and mass cytometry and single-cell RNA sequencing can readily measure the expression of a large numbe…
Learning to Retrieve Videos by Asking Questions
Avinash Madasu, Junier Oliva, Gedas Bertasius
The majority of traditional text-to-video retrieval systems operate in static environments, i.e., there is no interaction between the user and the agent beyond the initial textual…
Posterior Matching for Arbitrary Conditioning
Ryan R. Strauss, Junier B. Oliva
Arbitrary conditioning is an important problem in unsupervised learning, where we seek to model the conditional densities that underly some data…
Transparent Single-Cell Set Classification with Kernel Mean Embeddings
Siyuan Shan, Vishal Baskaran, Haidong Yi +3
Modern single-cell flow and mass cytometry technologies measure the expression of several proteins of the individual cells within a blood or tissue sample. Each profiled biological…
Adversarial Scrubbing of Demographic Information for Text Classification
Somnath Basu Roy Chowdhury, Sayan Ghosh, Yiyuan Li +3
Contextual representations learned by language models can often encode undesirable attributes, like demographic associations of the users, while being trained for an unrelated targ…
Towards Robust Active Feature Acquisition
Yang Li, Siyuan Shan, Qin Liu +1
Truly intelligent systems are expected to make critical decisions with incomplete and uncertain data. Active feature acquisition (AFA), where features are sequentially acquired to…
Partially Observed Exchangeable Modeling
Yang Li, Junier B. Oliva
Modeling dependencies among features is fundamental for many machine learning tasks. Although there are often multiple related instances that may be leveraged to inform conditional…
Arbitrary Conditional Distributions with Energy
Ryan R. Strauss, Junier B. Oliva
Modeling distributions of covariates, or density estimation, is a core challenge in unsupervised learning. However, the majority of work only considers the joint distribution, whic…
NRTSI: Non-Recurrent Time Series Imputation
Siyuan Shan, Yang Li, Junier B. Oliva
Time series imputation is a fundamental task for understanding time series with missing data. Existing methods either do not directly handle irregularly-sampled data or degrade sev…
Unsupervised Imputation of Non-ignorably Missing Data Using Importance-Weighted Autoencoders
David K. Lim, Naim U. Rashid, Junier B. Oliva +1
Deep Learning (DL) methods have dramatically increased in popularity in recent years. While its initial success was demonstrated in the classification and manipulation of image dat…
Multiscale Score Matching for Out-of-Distribution Detection
Ahsan Mahmood, Junier Oliva, Martin Styner
We present a new methodology for detecting out-of-distribution (OOD) images by utilizing norms of the score estimates at multiple noise scales. A score is defined to be the gradien…
Active Feature Acquisition with Generative Surrogate Models
Yang Li, Junier B. Oliva
Many real-world situations allow for the acquisition of additional relevant information when making an assessment with limited or uncertain data. However, traditional ML approaches…
Exchangeable Neural ODE for Set Modeling
Yang Li, Haidong Yi, Christopher M. Bender +2
Reasoning over an instance composed of a set of vectors, like a point cloud, requires that one accounts for intra-set dependent features among elements. However, since such instanc…
Deep Goal-Oriented Clustering
Yifeng Shi, Christopher M. Bender, Junier B. Oliva +1
Clustering and prediction are two primary tasks in the fields of unsupervised and supervised learning, respectively. Although much of the recent advances in machine learning have b…
Dynamic Feature Acquisition with Arbitrary Conditional Flows
Yang Li, Junier B. Oliva
Many real-world situations allow for the acquisition of additional relevant information when making an assessment with limited or uncertain data. However, traditional ML approaches…
Defense Through Diverse Directions
Christopher M. Bender, Yang Li, Yifeng Shi +2
In this work we develop a novel Bayesian neural network methodology to achieve strong adversarial robustness without the need for online adversarial training. Unlike previous effor…
Deep Message Passing on Sets
Yifeng Shi, Junier Oliva, Marc Niethammer
Modern methods for learning over graph input data have shown the fruitfulness of accounting for relationships among elements in a collection. However, most methods that learn over…
Meta-Neighborhoods
Siyuan Shan, Yang Li, Junier Oliva
Making an adaptive prediction based on one's input is an important ability for general artificial intelligence. In this work, we step forward in this direction and propose a semi-p…