Infinity Learning: Learning Markov Chains from Aggregate Steady-State Observations

by   Jianfei Gao, et al.

We consider the task of learning a parametric Continuous Time Markov Chain (CTMC) sequence model without examples of sequences, where the training data consists entirely of aggregate steady-state statistics. Making the problem harder, we assume that the states we wish to predict are unobserved in the training data. Specifically, given a parametric model over the transition rates of a CTMC and some known transition rates, we wish to extrapolate its steady state distribution to states that are unobserved. A technical roadblock to learn a CTMC from its steady state has been that the chain rule to compute gradients will not work over the arbitrarily long sequences necessary to reach steady state —from where the aggregate statistics are sampled. To overcome this optimization challenge, we propose ∞-SGD, a principled stochastic gradient descent method that uses randomly-stopped estimators to avoid infinite sums required by the steady state computation, while learning even when only a subset of the CTMC states can be observed. We apply ∞-SGD to a real-world testbed and synthetic experiments showcasing its accuracy, ability to extrapolate the steady state distribution to unobserved states under unobserved conditions (heavy loads, when training under light loads), and succeeding in difficult scenarios where even a tailor-made extension of existing methods fails.



page 7


Steady state availability general equations of decision and sequential processes in Continuous Time Markov Chain models

Continuous Time Markov Chain (CMTC) is widely used to describe and analy...

Correcting for Non-Markovian Asymptotic Effects using Markovian Representation

Asymptotic properties of Markov Processes, such as steady state probabil...

On Markov Chain Gradient Descent

Stochastic gradient methods are the workhorse (algorithms) of large-scal...

The Platform Design Problem

On-line firms deploy suites of software platforms, where each platform i...

Continuous Time Markov Chains for Analysis of Non-Alcoholic Fatty liver Disease Evolution

In the present paper, progression of non-alcoholic fatty liver disease (...

Sharp convergence to steady states of Allen-Cahn

In our recent work we found a surprising breakdown of symmetry conservat...

A Case Study on the Parametric Occurrence of Multiple Steady States

We consider the problem of determining multiple steady states for positi...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.