Glaser, P; Arbel, M; Gretton, A; (2021) KALE Flow: A Relaxed KL Gradient Flow for Probabilities with Disjoint Support. In: Ranzato, M and Beygelzimer, A and Dauphin, Y and Liang, PS and Wortman Vaughan, J, (eds.) Advances in Neural Information Processing Systems 34 (NeurIPS 2021). (pp. pp. 8018-8031). NeurIPS

Preview

Text kale_flow_a_relaxed_kl_gradien.pdf - Published Version Download (1MB) | Preview

Abstract

We study the gradient flow for a relaxed approximation to the Kullback-Leibler (KL) divergence between a moving source and a fixed target distribution. This approximation, termed the KALE (KL Approximate Lower bound Estimator), solves a regularized version of the Fenchel dual problem defining the KL over a restricted class of functions. When using a Reproducing Kernel Hilbert Space (RKHS) to define the function class, we show that the KALE continuously interpolates between the KL and the Maximum Mean Discrepancy (MMD). Like the MMD and other Integral Probability Metrics, the KALE remains well-defined for mutually singular distributions. Nonetheless, the KALE inherits from the limiting KL a greater sensitivity to mismatch in the support of the distributions, compared with the MMD. These two properties make the KALE gradient flow particularly well suited when the target distribution is supported on a low-dimensional manifold. Under an assumption of sufficient smoothness of the trajectories, we show the global convergence of the KALE flow. We propose a particle implementation of the flow given initial samples from the source and the target distribution, which we use to empirically confirm the KALE’s properties.

Download activity - last month

Export as JSONCSVXML

Download activity - last 12 months

Export as XMLCSVJSON

Downloads by country - last 12 months

Export as JSONXMLCSV

Archive Staff Only

View Item