25 citations · 48 across the 13 of their papers we have counts for
18 papers
On stochastic stability of systems driven by red noise
Balázs Gerencsér, Miklós Rásonyi
We consider discrete-time non-linear stochastic dynamical systems where the driving noise is not i.i.d. but an autoregressive process (``red noise''). Under a standard dissipativit…
What if we knew what the future brings? Optimal investment for a frontrunner with price impact
Peter Bank, Yan Dolinsky, Miklós Rásonyi
In this paper we study optimal investment when the investor can peek some time units into the future, but cannot fully take advantage of this knowledge because of quadratic transac…
On the stability of the stochastic gradient Langevin algorithm with dependent data stream
Miklós Rásonyi, Kinga Tikosi
We prove, under mild conditions, that the stochastic gradient Langevin dynamics converges to a limiting law as time tends to infinity, even in the case where the driving data seque…
Taming neural networks with TUSLA: Non-convex learning via adaptive stochastic gradient Langevin algorithms
Attila Lovas, Iosif Lytras, Miklós Rásonyi +1
Artificial neural networks (ANNs) are typically highly nonlinear systems which are finely tuned via the optimization of their associated, non-convex loss functions. In many cases,…
Optimal long-term investment in illiquid markets when prices have negative memory
Miklós Rásonyi, Lóránt Nagy
In a discrete-time financial market model with instantaneous price impact, we find an asymptotically optimal strategy for an investor maximizing her expected wealth. The asset pric…
Ergodic theorems for queuing systems with dependent inter-arrival times
Attila Lovas, Miklós Rásonyi
We study a G/GI/1 single-server queuing model with i.i.d.\ service times that are independent of a stationary process of inter-arrival times. We show that the distribution of the w…
Invariant measures for multidimensional fractional stochastic volatility models
Balázs Gerencsér, Miklós Rásonyi
We establish convergence to an invariant measure as time tends to infinity, for a large class of (possibly non-Markovian) stochastic volatility models. Our arguments are based on a…
Markov chains in random environment with applications in queueing theory and machine learning
Attila Lovas, Miklós Rásonyi
We prove the existence of limiting distributions for a large class of Markov chains on a general state space in a random environment. We assume suitable versions of the standard dr…
Learning Threshold-Type Investment Strategies with Stochastic Gradient Method
Zsolt Nika, Miklós Rásonyi
In online portfolio optimization the investor makes decisions based on new, continuously incoming information on financial assets (typically their prices). In our study we consider…
On stochastic gradient Langevin dynamics with dependent data streams: the fully non-convex case
Ngoc Huy Chau, Éric Moulines, Miklos Rásonyi +2
We consider the problem of sampling from a target distribution, which is \emph {not necessarily logconcave}, in the context of empirical risk minimization and stochastic optimizati…
On stochastic gradient Langevin dynamics with dependent data streams in the logconcave case
M. Barkhagen, N. H. Chau, É. Moulines +3
We study the problem of sampling from a probability distribution on $\rset^d$ which has a density \wrt\ the Lebesgue measure known up to a normalization factor $x \mapsto \rme^…
On Utility Maximisation Under Model Uncertainty in Discrete-Time Markets
Miklós Rásonyi, Andrea Meireles-Rodrigues
We study the problem of maximising terminal utility for an agent facing model uncertainty, in a frictionless discrete-time market with one safe asset and finitely many risky assets…
On fixed gain recursive estimators with discontinuity in the parameters
Huy N. Chau, Chaman Kumar, Miklós Rásonyi +1
In this paper we estimate the tracking error of a fixed gain stochastic approximation scheme. The underlying process is not assumed Markovian, a mixing condition is required instea…
Non-concave optimal investment and no-arbitrage: a measure theoretical approach
Romain Blanchard, Laurence Carassus, Miklós Rásonyi
We consider non-concave and non-smooth random utility functions with do- main of definition equal to the non-negative half-line. We use a dynamic pro- gramming framework together w…
Non-convex dynamic programming and optimal investment
Teemu Penannen, Ari-Pekka Perkkiö, Miklós Rásonyi
We establish the existence of minimizers in a rather general setting of dynamic stochastic optimization without assuming either convexity or coercivity of the objective function. W…
An explicit solution for optimal investment problems with autoregressive prices and exponential utility
Sándor Deák, Miklós Rásonyi
We calculate explicitly the optimal strategy for an investor with exponential utility function when the stock price follows an autoregressive Gaussian process. We also calculate it…
Optimal investment under behavioural criteria -- a dual approach
Miklós Rásonyi, José G. Rodríguez-Villarreal
We consider a discrete-time, generically incomplete market model and a behavioural investor with power-like utility and distortion functions. The existence of optimal strategies in…
Hiding a drift
Miklós Rásonyi, Walter Schachermayer, Richard Warnung
In this article we consider a Brownian motion with drift of the form \[dS_t=μ_t dt+dB_t\qquadfor t\ge0,\] with a specific nontrivial , predictable with respect to $…