Solving Schr\"odinger Bridges via Maximum Likelihood

• URL: http://arxiv.org/abs/2106.02081v1
• Date: Thu, 3 Jun 2021 18:58:12 GMT
• Title: Solving Schr\"odinger Bridges via Maximum Likelihood
• Authors: Francisco Vargas, Pierre Thodoroff, Neil D. Lawrence, Austen Lamacraft
• Abstract summary: The Schr"odinger bridge problem (SBP) finds the most likely evolution between two probability distributions. We prove an equivalence between the SBP and maximum likelihood estimation enabling direct application of successful machine learning techniques.
• Score: 10.941628374136519
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The Schr\"odinger bridge problem (SBP) finds the most likely stochastic evolution between two probability distributions given a prior stochastic evolution. As well as applications in the natural sciences, problems of this kind have important applications in machine learning such as dataset alignment and hypothesis testing. Whilst the theory behind this problem is relatively mature, scalable numerical recipes to estimate the Schr\"odinger bridge remain an active area of research. We prove an equivalence between the SBP and maximum likelihood estimation enabling direct application of successful machine learning techniques. We propose a numerical procedure to estimate SBPs using Gaussian process and demonstrate the practical usage of our approach in numerical simulations and experiments.

Related papers

• Score matching for sub-Riemannian bridge sampling [2.048226951354646]
  Recent progress in machine learning can be modified to allow training of score approximators on sub-Riemannian gradients. We perform numerical experiments exemplifying samples from the bridge process on the Heisenberg group and the concentration of this process for small time.
  arXiv  Detail & Related papers  (2024-04-23T17:45:53Z)
• Generalized Schrödinger Bridge Matching [54.171931505066]
  Generalized Schr"odinger Bridge (GSB) problem setup is prevalent in many scientific areas both within and without machine learning. We propose Generalized Schr"odinger Bridge Matching (GSBM), a new matching algorithm inspired by recent advances. We show that such a generalization can be cast as solving conditional optimal control, for which variational approximations can be used.
  arXiv  Detail & Related papers  (2023-10-03T17:42:11Z)
• Qubit Dynamics beyond Lindblad: Non-Markovianity versus Rotating Wave Approximation [0.0]
  Even subtle effects in the interaction between qubits and environmental degrees of freedom become progressively relevant and experimentally visible. This applies particularly to the timescale separations that are at the basis of the most commonly used numerical simulation platform for qubit operations. We shed light on the questions (i) to which extent it is possible to monitor violations of either of these timescale separations experimentally and (ii) which of them is the most severe to provide highly accurate predictions.
  arXiv  Detail & Related papers  (2023-08-11T09:16:07Z)
• Building the Bridge of Schr\"odinger: A Continuous Entropic Optimal Transport Benchmark [96.06787302688595]
  We propose a novel way to create pairs of probability distributions for which the ground truth OT solution is known by the construction. We use these benchmark pairs to test how well existing neural EOT/SB solvers actually compute the EOT solution.
  arXiv  Detail & Related papers  (2023-06-16T20:03:36Z)
• Provably Convergent Schr\"odinger Bridge with Applications to Probabilistic Time Series Imputation [21.27702285561771]
  We present a first convergence analysis of the Schr"odinger bridge algorithm based on approximated projections. As for its practical applications, we apply SBP to probabilistic time series imputation by generating missing values conditioned on observed data.
  arXiv  Detail & Related papers  (2023-05-12T04:39:01Z)
• Aligned Diffusion Schrödinger Bridges [41.95944857946607]
  Diffusion Schr"odinger bridges (DSBs) have recently emerged as a powerful framework for recovering dynamics via their marginal observations at different time points. Existing algorithms for solving DSBs have so far failed to utilize the structure of aligned data. We propose a novel algorithmic framework that, for the first time, solves DSBs while respecting the data alignment.
  arXiv  Detail & Related papers  (2023-02-22T14:55:57Z)
• Importance sampling for stochastic quantum simulations [68.8204255655161]
  We introduce the qDrift protocol, which builds random product formulas by sampling from the Hamiltonian according to the coefficients. We show that the simulation cost can be reduced while achieving the same accuracy, by considering the individual simulation cost during the sampling stage. Results are confirmed by numerical simulations performed on a lattice nuclear effective field theory.
  arXiv  Detail & Related papers  (2022-12-12T15:06:32Z)
• Gaussian Process regression over discrete probability measures: on the non-stationarity relation between Euclidean and Wasserstein Squared Exponential Kernels [0.19116784879310028]
  A non-stationarity relationship between the Wasserstein-based squared exponential kernel and its Euclidean-based counterpart is studied. A transformation is used to transform the input space as Euclidean into a non-stationary and Wasserstein-based Gaussian Process model.
  arXiv  Detail & Related papers  (2022-12-02T17:09:52Z)
• Sequential Permutation Testing of Random Forest Variable Importance Measures [68.8204255655161]
  It is proposed here to use sequential permutation tests and sequential p-value estimation to reduce the high computational costs associated with conventional permutation tests. The results of simulation studies confirm that the theoretical properties of the sequential tests apply. The numerical stability of the methods is investigated in two additional application studies.
  arXiv  Detail & Related papers  (2022-06-02T20:16:50Z)
• Causal Inference Under Unmeasured Confounding With Negative Controls: A Minimax Learning Approach [84.29777236590674]
  We study the estimation of causal parameters when not all confounders are observed and instead negative controls are available. Recent work has shown how these can enable identification and efficient estimation via two so-called bridge functions.
  arXiv  Detail & Related papers  (2021-03-25T17:59:19Z)
• Marginal likelihood computation for model selection and hypothesis testing: an extensive review [66.37504201165159]
  This article provides a comprehensive study of the state-of-the-art of the topic. We highlight limitations, benefits, connections and differences among the different techniques. Problems and possible solutions with the use of improper priors are also described.
  arXiv  Detail & Related papers  (2020-05-17T18:31:58Z)

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.