Sampling Approximately Low-Rank Ising Models: MCMC meets Variational Methods
February 17, 2022 ยท Declared Dead ยท ๐ Annual Conference Computational Learning Theory
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Frederic Koehler, Holden Lee, Andrej Risteski
arXiv ID
2202.08907
Category
cs.DS: Data Structures & Algorithms
Cross-listed
cs.LG,
math.PR,
stat.ML
Citations
26
Venue
Annual Conference Computational Learning Theory
Last Checked
3 months ago
Abstract
We consider Ising models on the hypercube with a general interaction matrix $J$, and give a polynomial time sampling algorithm when all but $O(1)$ eigenvalues of $J$ lie in an interval of length one, a situation which occurs in many models of interest. This was previously known for the Glauber dynamics when *all* eigenvalues fit in an interval of length one; however, a single outlier can force the Glauber dynamics to mix torpidly. Our general result implies the first polynomial time sampling algorithms for low-rank Ising models such as Hopfield networks with a fixed number of patterns and Bayesian clustering models with low-dimensional contexts, and greatly improves the polynomial time sampling regime for the antiferromagnetic/ferromagnetic Ising model with inconsistent field on expander graphs. It also improves on previous approximation algorithm results based on the naive mean-field approximation in variational methods and statistical physics. Our approach is based on a new fusion of ideas from the MCMC and variational inference worlds. As part of our algorithm, we define a new nonconvex variational problem which allows us to sample from an exponential reweighting of a distribution by a negative definite quadratic form, and show how to make this procedure provably efficient using stochastic gradient descent. On top of this, we construct a new simulated tempering chain (on an extended state space arising from the Hubbard-Stratonovich transform) which overcomes the obstacle posed by large positive eigenvalues, and combine it with the SGD-based sampler to solve the full problem.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Data Structures & Algorithms
R.I.P.
๐ป
Ghosted
R.I.P.
๐ป
Ghosted
Relief-Based Feature Selection: Introduction and Review
R.I.P.
๐ป
Ghosted
Route Planning in Transportation Networks
R.I.P.
๐ป
Ghosted
Near-linear time approximation algorithms for optimal transport via Sinkhorn iteration
R.I.P.
๐ป
Ghosted
Hierarchical Clustering: Objective Functions and Algorithms
R.I.P.
๐ป
Ghosted
Graph Isomorphism in Quasipolynomial Time
Died the same way โ ๐ป Ghosted
R.I.P.
๐ป
Ghosted
Language Models are Few-Shot Learners
R.I.P.
๐ป
Ghosted
PyTorch: An Imperative Style, High-Performance Deep Learning Library
R.I.P.
๐ป
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
๐ป
Ghosted