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 $x_o$: $p(x_u \mid x_o)$.
no code implementations • 4 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.
1 code implementation • 4 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.
1 code implementation • 28 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.
no code implementations • 3 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.
1 code implementation • 18 Mar 2024 • Boqi Chen, Junier Oliva, Marc Niethammer
Medical records often consist of different modalities, such as images, text, and tabular information.
no code implementations • 6 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.
no code implementations • 27 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.
1 code implementation • 11 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.
1 code implementation • 18 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.
no code implementations • ICLR 2022 • Christopher M Bender, Patrick Emmanuel, Michael K. Reiter, Junier Oliva
Neural networks have enabled learning over examples that contain thousands of dimensions.
no code implementations • 29 Sep 2021 • John Kenton Moore, Junier Oliva
This work develops a novel black box optimization technique for learning robust policies for stochastic environments.
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.
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.
no code implementations • 21 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.
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.
2 code implementations • 31 May 2019 • Mariya Popova, Mykhailo Shvets, Junier Oliva, Olexandr Isayev
Designing new molecules with a set of predefined properties is a core problem in modern drug discovery and development.
Ranked #1 on
Molecular Graph Generation
on MOSES
1 code implementation • 5 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.
no code implementations • 6 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.
no code implementations • 29 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.
no code implementations • 27 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.