14 citations · 24 across the 13 of their papers we have counts for
15 papers
ADDQ: Adaptive Distributional Double Q-Learning
Leif Döring, Benedikt Wille, Maximilian Birr +2
Bias problems in the estimation of -values are a well-known obstacle that slows down convergence of -learning and actor-critic methods. One of the reasons of the success of m…
Gradient Span Algorithms Make Predictable Progress in High Dimension
Felix Benning, Leif Döring
We prove that all 'gradient span algorithms' have asymptotically deterministic behavior on scaled Gaussian random functions as the dimension tends to infinity. This is a functional…
Almost sure convergence rates of stochastic gradient methods under gradient domination
Simon Weissmann, Sara Klein, Waïss Azizian +1
Stochastic gradient methods are among the most important algorithms in training machine learning problems. While classical assumptions such as strong convexity allow a simple analy…
Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods
Sara Klein, Simon Weissmann, Leif Döring
Markov Decision Processes (MDPs) are a formal framework for modeling and solving sequential decision-making problems. In finite-time horizons such problems are relevant for instanc…
Random Function Descent
Felix Benning, Leif Döring
Classical worst-case optimization theory neither explains the success of optimization in machine learning, nor does it help with step size selection. In this paper we demonstrate t…
Existence and uniqueness results for time-inhomogeneous time-change equations and Fokker--Planck equations
Leif Döring, Lukas Gonon, David J. Prömel +1
We prove existence and uniqueness of solutions to Fokker--Planck equations associated to Markov operators multiplicatively perturbed by degenerate time-inhomogeneous coefficients.…
On Skorokhod Embeddings and Poisson Equations
Leif Doering, Lukas Gonon, David J. Prömel +1
The classical Skorokhod embedding problem for a Brownian motion asks to find a stopping time so that is distributed according to a prescribed probability distribution…
Functional Analytic (Ir-)Regularity Properties of SABR-type Processes
Leif Doering, Blanka Horvath, Josef Teichmann
The SABR model is a benchmark stochastic volatility model in interest rate markets, which has received much attention in the past decade. Its popularity arose from a tractable asym…
Finite system scheme for infinite rate mutually catalytic branching with infinite branching rate
Leif Doering, Achim Klenke, Leonid Mytnik
For many stochastic diffusion processes with mean field interaction, convergence of the rescaled total mass processes towards a diffusion process is known. Here we show convergence…
Real Self-Similar Processes Started from the Origin
Steffen Dereich, Leif Doering, Andreas E. Kyprianou
Since the seminal work of Lamperti there is a lot of interest in the understanding of the general structure of self-similar Markov processes. Lamperti gave a representation of posi…
Perpetual Integrals for Levy Processes
Leif Doering, Andreas E. Kyprianou
We ask for necessary and sufficient conditions for almost sure finiteness of the perpetual integrals of a Levy process. Zero-one laws are already known for Brownian motion with dri…
Stationarity and ergodicity for an affine two factor model
Matyas Barczy, Leif Doering, Zenghu Li +1
We study the existence of a unique stationary distribution and ergodicity for a 2-dimensional affine process. The first coordinate is supposed to be a so-called alpha-root process…
On entire moments of self-similar Markov processes
Matyas Barczy, Leif Doering
It has been shown by Bertoin and Yor (2002) that the law of positive self-similar Markov processes (pssMps) that only jump downwards and do not hit zero in finite time are uniquely…
A Jump Type SDE Approach to Positive Self-Similar Markov Processes
Leif Doering, Matyas Barczy
We present a new approach to positive self-similar Markov processes (pssMps) by reformulating Lamperti's transformation via jump type SDEs. As applications, we give direct construc…
Longtime Behavior for Mutually Catalytic Branching with Negative Correlations
Leif Doering, Leonid Mytnik
In several examples, dualities for interacting diffusion and particle systems permit the study of the longtime behavior of solutions. A particularly difficult model in which many t…