RNNs can sustain power-law forgetting and multi-time-scale learning when heavy-tailed fluctuations in SGD balance the collapse tendency toward short time scales, governed by a spectral exponent β.
An Introduction to L\'evy and Feller Processes. Advanced Courses in Mathematics - CRM Barcelona 2014
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
These lecture notes are an extended version of my lectures on L\'evy and L\'evy-type (Feller) processes given at the "Second Barcelona Summer School on Stochastic Analysis" 2014 organized by the Centre de Recerca Matemaatica (CRM). The lectures are aimed at advanced graduate and PhD students. In order to read these notes, one should have sound knowledge of measure theoretic probability theory and some background in stochastic processes, as it is covered in my books "Measures, Integals and Martingales" (Cambridge University Press) and "Brownian Motion" (de Gruyter). My purpose in these lectures is to give an introduction to Levy processes, and to show how one can extend this approach to space inhomogeneous processes which behave locally like L\'evy processes: L\'evy-type or Feller processes. These course notes will be published, together Davar Khoshnevisan's notes on "Invariance and Comparison Principles for Parabolic SPDEs" as "From L\'evy-Type Processes to Parabolic SPDEs" by the CRM, Barcelona and Birk\"auser, Cham 2017 (ISBN: 978-3-319-34119-4). The arXiv-version and the published version may differ in layout, pagination and wording, but not in content
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Anti-Collapse Dynamics and the Emergence of Multi-Time-Scale Learning in Recurrent Neural Networks
RNNs can sustain power-law forgetting and multi-time-scale learning when heavy-tailed fluctuations in SGD balance the collapse tendency toward short time scales, governed by a spectral exponent β.