A Polynomial Time MCMC Method for Sampling from Continuous DPPs

We study the Gibbs sampling algorithm for continuous determinantal point processes. We show that, given a warm start, the Gibbs sampler generates a random sample from a continuous $k$-DPP defined on a $d$-dimensional domain by only taking $\text{poly}(k)$ number of steps. As an application, we design an algorithm to generate random samples from $k$-DPPs defined by a spherical Gaussian kernel on a unit sphere in $d$-dimensions, $\mathbb{S}^{d-1}$ in time polynomial in $k,d$.

[1]  Suvrit Sra,et al.  Fast Mixing Markov Chains for Strongly Rayleigh Measures, DPPs, and Constrained Sampling , 2016, NIPS.

[2]  Milena Mihail.  On the Expansion of Combinatorial Polytopes , 1992, MFCS.

[3]  S. Meyn,et al.  Geometric ergodicity and the spectral gap of non-reversible Markov chains , 2009, 0906.5322.

[4]  M. L. Mehta,et al.  ON THE DENSITY OF EIGENVALUES OF A RANDOM MATRIX , 1960 .

[5]  Ben Taskar,et al.  Expectation-Maximization for Learning Determinantal Point Processes , 2014, NIPS.

[6]  J. A. Fill.  Eigenvalue bounds on convergence to stationarity for nonreversible markov chains , 1991 .

[7]  Y. Peres,et al.  Determinantal Processes and Independence , 2005, math/0503110.

[8]  J. Møller,et al.  Determinantal point process models and statistical inference , 2012, 1205.4818.

[9]  A. Hardy,et al.  Monte Carlo with determinantal point processes , 2016, The Annals of Applied Probability.

[10]  Nima Anari,et al.  Monte Carlo Markov Chain Algorithms for Sampling Strongly Rayleigh Distributions and Determinantal Point Processes , 2016, COLT.

[11]  Amin Karbasi,et al.  Fast Mixing for Discrete Point Processes , 2015, COLT.

[12]  J. Ginibre.  Statistical Ensembles of Complex, Quaternion, and Real Matrices , 1965 .

[13]  E. Rains,et al.  Eynard–Mehta Theorem, Schur Process, and their Pfaffian Analogs , 2004, math-ph/0409059.

[14]  Ben Taskar,et al.  Discovering Diverse and Salient Threads in Document Collections , 2012, EMNLP.

[15]  Miklós Simonovits,et al.  Random Walks in a Convex Body and an Improved Volume Algorithm , 1993, Random Struct. Algorithms.

[16]  Ankur Moitra,et al.  Learning Determinantal Point Processes with Moments and Cycles , 2017, ICML.

[17]  Ege Holger Rubak,et al.  Statistical aspects of determinantal point processes , 2012 .

[18]  Kasturi R. Varadarajan,et al.  Sampling-based dimension reduction for subspace approximation , 2007, STOC '07.

[19]  Yuval Peres,et al.  Zeros of the i.i.d. Gaussian power series: a conformally invariant determinantal process , 2003, math/0310297.

[20]  A. Sokal,et al.  Bounds on the ² spectrum for Markov chains and Markov processes: a generalization of Cheeger’s inequality , 1988 .

[21]  O. Macchi.  The coincidence approach to stochastic point processes , 1975, Advances in Applied Probability.

[22]  Ben Taskar,et al.  Determinantal Point Processes for Machine Learning , 2012, Found. Trends Mach. Learn..

[23]  Roman Garnett,et al.  Exact Sampling from Determinantal Point Processes , 2016, ArXiv.

[24]  Ben Taskar,et al.  Structured Determinantal Point Processes , 2010, NIPS.

[25]  Suvrit Sra,et al.  Efficient Sampling for k-Determinantal Point Processes , 2015, AISTATS.

[26]  K. Johansson.  Non-intersecting paths, random tilings and random matrices , 2000, math/0011250.

[27]  D. Freedman.  On Markov Chains with Continuous State Space , 1997 .

[28]  R. Pemantle,et al.  Local Characteristics, Entropy and Limit Theorems for Spanning Trees and Domino Tilings Via Transfer-Impedances , 1993, math/0404048.

[29]  Chase E. Zachary,et al.  Statistical properties of determinantal point processes in high-dimensional Euclidean spaces. , 2008, Physical review. E, Statistical, nonlinear, and soft matter physics.

[30]  Ben Taskar,et al.  Approximate Inference in Continuous Determinantal Point Processes , 2013, ArXiv.

[31]  Ben Taskar,et al.  k-DPPs: Fixed-Size Determinantal Point Processes , 2011, ICML.

[32]  Luis Rademacher,et al.  Efficient Volume Sampling for Row/Column Subset Selection , 2010, 2010 IEEE 51st Annual Symposium on Foundations of Computer Science.

[33]  Yuan Yao,et al.  Mercer's Theorem, Feature Maps, and Smoothing , 2006, COLT.