Search Results for author: Junier Oliva

Found 21 papers, 11 papers with code

ACFlow: Flow Models for Arbitrary Conditional Likelihoods

1 code implementation ICML 2020 Yang Li, Shoaib Akbar, Junier Oliva

However, a majority of generative modeling approaches are focused solely on the joint distribution $p(x)$ and utilize models where it is intractable to obtain the conditional distribution of some arbitrary subset of features $x_u$ given the rest of the observed covariates $x_o$: $p(x_u \mid x_o)$.

Imputation

Towards Cost Sensitive Decision Making

no code implementations4 Oct 2024 Yang Li, Junier Oliva

In order to assist the agent in the actively-acquired partially-observed environment and alleviate the exploration-exploitation dilemma, we develop a model-based approach, where a deep generative model is utilized to capture the dependencies of the features and impute the unobserved features.

Decision Making

Distribution Guided Active Feature Acquisition

1 code implementation4 Oct 2024 Yang Li, Junier Oliva

First, we show how to build generative models that can capture dependencies over arbitrary subsets of features and employ these models for acquisitions in a greedy scheme.

Localizing Anomalies via Multiscale Score Matching Analysis

1 code implementation28 Jun 2024 Ahsan Mahmood, Junier Oliva, Martin Styner

This paper introduces Spatial-MSMA (Multiscale Score Matching Analysis), a novel unsupervised method for anomaly localization in volumetric brain MRIs.

Anomaly Detection Anomaly Localization +1

EMOE: Expansive Matching of Experts for Robust Uncertainty Based Rejection

no code implementations3 Jun 2024 Yunni Qu, James Wellnitz, Alexander Tropsha, Junier Oliva

Expansive Matching of Experts (EMOE) is a novel method that utilizes support-expanding, extrapolatory pseudo-labeling to improve prediction and uncertainty based rejection on out-of-distribution (OOD) points.

Data Augmentation

A Unified Model for Longitudinal Multi-Modal Multi-View Prediction with Missingness

1 code implementation18 Mar 2024 Boqi Chen, Junier Oliva, Marc Niethammer

Medical records often consist of different modalities, such as images, text, and tabular information.

Anomaly Detection via Gumbel Noise Score Matching

no code implementations6 Apr 2023 Ahsan Mahmood, Junier Oliva, Martin Styner

We propose Gumbel Noise Score Matching (GNSM), a novel unsupervised method to detect anomalies in categorical data.

Anomaly Detection Segmentation

Acquisition Conditioned Oracle for Nongreedy Active Feature Acquisition

no code implementations27 Feb 2023 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 acquisition costs whilst still yielding accurate predictions.

Decision Making

Learning to Retrieve Videos by Asking Questions

1 code implementation11 May 2022 Avinash Madasu, Junier Oliva, Gedas Bertasius

To overcome this limitation, we propose a novel framework for Video Retrieval using Dialog (ViReD), which enables the user to interact with an AI agent via multiple rounds of dialog, where the user refines retrieved results by answering questions generated by an AI agent.

AI Agent Retrieval +2

Transparent Single-Cell Set Classification with Kernel Mean Embeddings

1 code implementation18 Jan 2022 Siyuan Shan, Vishal Baskaran, Haidong Yi, Jolene Ranek, Natalie Stanley, Junier Oliva

Each profiled biological sample is thus represented by a set of hundreds of thousands of multidimensional cell feature vectors, which incurs a high computational cost to predict each biological sample's associated phenotype with machine learning models.

BIG-bench Machine Learning Classification

Hypothesis Driven Coordinate Ascent for Reinforcement Learning

no code implementations29 Sep 2021 John Kenton Moore, Junier Oliva

This work develops a novel black box optimization technique for learning robust policies for stochastic environments.

MuJoCo OpenAI Gym +3

Arbitrary Conditional Distributions with Energy

1 code implementation NeurIPS 2021 Ryan Strauss, Junier Oliva

A more general and useful problem is arbitrary conditional density estimation, which aims to model any possible conditional distribution over a set of covariates, reflecting the more realistic setting of inference based on prior knowledge.

Arbitrary Conditional Density Estimation Imputation

Multiscale Score Matching for Out-of-Distribution Detection

1 code implementation ICLR 2021 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.

Out-of-Distribution Detection

Deep Message Passing on Sets

no code implementations21 Sep 2019 Yifeng Shi, Junier Oliva, Marc Niethammer

DMPS not only connects learning on graphs with learning on sets via deep kernel learning, but it also bridges message passing on sets and traditional diffusion dynamics commonly used in denoising models.

Denoising Relational Reasoning

Meta-Neighborhoods

1 code implementation NeurIPS 2020 Siyuan Shan, Yang Li, Junier Oliva

Making an adaptive prediction based on one's input is an important ability for general artificial intelligence.

Meta-Learning Multi-Task Learning

Exchangeable Generative Models with Flow Scans

1 code implementation5 Feb 2019 Christopher Bender, Kevin O'Connor, Yang Li, Juan Jose Garcia, Manzil Zaheer, Junier Oliva

In this work, we develop a new approach to generative density estimation for exchangeable, non-i. i. d.

Density Estimation

Estimating Cosmological Parameters from the Dark Matter Distribution

no code implementations6 Nov 2017 Siamak Ravanbakhsh, Junier Oliva, Sebastien Fromenteau, Layne C. Price, Shirley Ho, Jeff Schneider, Barnabas Poczos

A major approach to estimating the cosmological parameters is to use the large-scale matter distribution of the Universe.

Bayesian Nonparametric Kernel-Learning

no code implementations29 Jun 2015 Junier Oliva, Avinava Dubey, Andrew G. Wilson, Barnabas Poczos, Jeff Schneider, Eric P. Xing

In this paper we introduce Bayesian nonparmetric kernel-learning (BaNK), a generic, data-driven framework for scalable learning of kernels.

Fast Function to Function Regression

no code implementations27 Oct 2014 Junier Oliva, Willie Neiswanger, Barnabas Poczos, Eric Xing, Jeff Schneider

Function to function regression (FFR) covers a large range of interesting applications including time-series prediction problems, and also more general tasks like studying a mapping between two separate types of distributions.

regression Time Series +1

Cannot find the paper you are looking for? You can Submit a new open access paper.