Scalable Learning and MAP Inference for Nonsymmetric Determinantal Point Processes

• URL: http://arxiv.org/abs/2006.09862v2
• Date: Tue, 13 Apr 2021 15:16:06 GMT
• Title: Scalable Learning and MAP Inference for Nonsymmetric Determinantal Point Processes
• Authors: Mike Gartrell, Insu Han, Elvis Dohmatob, Jennifer Gillenwater, Victor-Emmanuel Brunel
• Abstract summary: 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.
• Score: 29.56615511158156
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Exploring and Learning in Sparse Linear MDPs without Computationally Intractable Oracles [39.10180309328293]
  In this paper we revisit linear MDPs from the perspective of feature selection. Our main result is the first-time algorithm for this problem. We show that they do exist and can be computed efficiently via convex programming.
  arXiv  Detail & Related papers  (2023-09-18T03:35:48Z)
• Provably Efficient Representation Learning with Tractable Planning in Low-Rank POMDP [81.00800920928621]
  We study representation learning in partially observable Markov Decision Processes (POMDPs) We first present an algorithm for decodable POMDPs that combines maximum likelihood estimation (MLE) and optimism in the face of uncertainty (OFU) We then show how to adapt this algorithm to also work in the broader class of $gamma$-observable POMDPs.
  arXiv  Detail & Related papers  (2023-06-21T16:04:03Z)
• Scalable MCMC Sampling for Nonsymmetric Determinantal Point Processes [45.40646054226403]
  A determinantal point process (DPP) assigns a probability to every subset of $n$ items. Recent work has studied an approximate chain Monte Carlo sampling algorithm for NDPPs restricted to size-$k$ subsets. We develop a scalable MCMC sampling algorithm for $k$-NDPPs with low-rank kernels.
  arXiv  Detail & Related papers  (2022-07-01T15:22:12Z)
• Scalable Sampling for Nonsymmetric Determinantal Point Processes [47.18450267217498]
  A determinantal point process (DPP) on a collection of $M$ items is a model, parameterized by a symmetric kernel matrix. Recent work shows that removing the kernel symmetry constraint, yielding nonsymmetric DPPs (NDPPs), can lead to significant predictive performance gains for machine learning applications. There is only one known DPP sampling algorithm, based on Cholesky decomposition, that can directly apply to NDPPs as well. We show that imposing certain structural constraints on the NDPP kernel enables us to bound the rejection rate in a way that depends only on the kernel rank.
  arXiv  Detail & Related papers  (2022-01-20T19:21:59Z)
• Nearly Optimal Regret for Learning Adversarial MDPs with Linear Function Approximation [92.3161051419884]
  We study the reinforcement learning for finite-horizon episodic Markov decision processes with adversarial reward and full information feedback. We show that it can achieve $tildeO(dHsqrtT)$ regret, where $H$ is the length of the episode. We also prove a matching lower bound of $tildeOmega(dHsqrtT)$ up to logarithmic factors.
  arXiv  Detail & Related papers  (2021-02-17T18:54:08Z)
• Simple and Near-Optimal MAP Inference for Nonsymmetric DPPs [3.3504365823045044]
  We study the problem of maximum a posteriori (MAP) inference for determinantal point processes defined by a nonsymmetric kernel matrix. We obtain the first multiplicative approximation guarantee for this problem using local search. Our approximation factor of $kO(k)$ is nearly tight, and we show theoretically and experimentally that it compares favorably to the state-of-the-art methods for this problem.
  arXiv  Detail & Related papers  (2021-02-10T09:34:44Z)
• Provably Efficient Reinforcement Learning for Discounted MDPs with Feature Mapping [99.59319332864129]
  In this paper, we study reinforcement learning for discounted Decision (MDP) We propose a novel algorithm that makes use of the feature mapping and obtains a $tilde O(dsqrtT/ (1-gamma)2)$ regret. Our upper and lower bound results together suggest that the proposed reinforcement learning algorithm is near-optimal up to a $ (1-gamma)-0.5$ factor.
  arXiv  Detail & Related papers  (2020-06-23T17:08:54Z)
• Determinantal Point Processes in Randomized Numerical Linear Algebra [80.27102478796613]
  Numerical Linear Algebra (RandNLA) uses randomness to develop improved algorithms for matrix problems that arise in scientific computing, data science, machine learning, etc. Recent work has uncovered deep and fruitful connections between DPPs and RandNLA which lead to new guarantees and improved algorithms.
  arXiv  Detail & Related papers  (2020-05-07T00:39:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.