paper-with-me

Papers

Scalable Learning and MAP Inference for Nonsymmetric Determinantal Point Processes

2020-06-17 · ICLR 2021 1 · Mike Gartrell, Insu Han, Elvis Dohmatob, Jennifer Gillenwater, Victor-Emmanuel Brunel

Determinantal point processes (DPPs) have attracted significant attention in machine learning for their ability to model subsets drawn from a large item collection. Recent work shows that nonsymmetric DPP (NDPP) kernels have significant advantages over symmetric kernels in terms of modeling power and predictive performance. However, for an item collection of size $M$, existing NDPP learning and inference algorithms require memory quadratic in $M$ and runtime cubic (for learning) or quadratic (for inference) in $M$, making them impractical for many typical subset selection tasks. In this work, we develop a learning algorithm with space and time requirements linear in $M$ by introducing a new NDPP kernel decomposition. We also derive a linear-complexity NDPP maximum a posteriori (MAP) inference algorithm that applies not only to our new kernel but also to that of prior work. Through evaluation on real-world datasets, we show that our algorithms scale significantly better, and can match the predictive performance of prior work.

📄 PDF Abstract BibTeX arXiv:2006.09862

Code (2)

cgartrel/nonsymmetric-DPP-learning 공식 구현 pytorch
cgartrel/scalable-nonsymmetric-dpps pytorch

Tasks

Point Processes

Similar Papers 제목 키워드 기반

Online MAP Inference and Learning for Nonsymmetric Determinantal Point Processes

2021-11-29 · Aravind Reddy, Ryan A. Rossi, Zhao Song, Anup Rao 외

In this paper, we introduce the online and streaming MAP inference and learning problems for Non-symmetric Determinantal Point Processes (NDPPs) where data points arrive in an arbitrary order and the algorithms are const…

Point Processesvalid

Scalable Sampling for Nonsymmetric Determinantal Point Processes

2022-01-20 · ICLR 2022 4 · Insu Han, Mike Gartrell, Jennifer Gillenwater, Elvis Dohmatob 외

A determinantal point process (DPP) on a collection of $M$ items is a model, parameterized by a symmetric kernel matrix, that assigns a probability to every subset of those items. Recent work shows that removing the kern…

Point Processes

Scalable MCMC Sampling for Nonsymmetric Determinantal Point Processes

2022-07-01 · Insu Han, Mike Gartrell, Elvis Dohmatob, Amin Karbasi

A determinantal point process (DPP) is an elegant model that assigns a probability to every subset of a collection of $n$ items. While conventionally a DPP is parameterized by a symmetric kernel matrix, removing this sym…

Point Processes

Learning Nonsymmetric Determinantal Point Processes

2019-05-30 · NeurIPS 2019 12 · Mike Gartrell, Victor-Emmanuel Brunel, Elvis Dohmatob, Syrine Krichene

Determinantal point processes (DPPs) have attracted substantial attention as an elegant probabilistic model that captures the balance between quality and diversity within sets. DPPs are conventionally parameterized by a …

Information RetrievalPoint ProcessesRecommendation SystemsRetrieval

Structured Determinantal Point Processes

2010-12-01 · NeurIPS 2010 12 · Alex Kulesza, Ben Taskar

We present a novel probabilistic model for distributions over sets of structures -- for example, sets of sequences, trees, or graphs. The critical characteristic of our model is a preference for diversity: sets containin…

DiversityPoint ProcessesPose Estimation