Study analyzes a new algorithm for complex optimization problems.
problem Stochastic bilevel optimisation problems in continuous-time models.
method Continuous-time, two-timescale stochastic approximation algorithm.
result Obtained weak convergence rate using central limit theorem.
Continuous-time SGD converges to optimal parameters via CLT.
problem Learning continuous-time models efficiently.
method Stochastic gradient descent in continuous time (SGDCT).
result Proves a central limit theorem for SGDCT's convergence.
A new approach models exploration in continuous-time RL using random measures.
problem Modeling exploration in continuous-time reinforcement learning.
method Random measure approach to control execution in continuous-time RL.
result Grid-sampling limit SDE can replace existing models for theoretical analysis and learning algorithms.
Continuous time random walks impose a random waiting time before each particle jump. Scaling limits of heavy tailed continuous time random walks are governed by fractional evolution equations. Space-fractional derivatives describe heavy tailed jumps, and the time-fractional version codes heavy tailed waiting times. Thi…
New SDE model for continuous-time reinforcement learning.
problem Modeling exploration in continuous-time reinforcement learning.
method Introduced grid-sampling SDE as a proxy model.
result Wellposedness of the SDE in the presence of jumps.
Study high-frequency trading game with price impact, finding unique equilibrium.
problem Optimal execution in a trading game with transient price impact.
method Analyzes high-frequency limit of an n-trader optimal execution game. result High-frequency limit converges to a continuous-time model with quadratic costs.
Accelerated gradient methods play a central role in optimization, achieving optimal rates in many settings. While many generalizations and extensions of Nesterov's original acceleration method have been proposed, it is not yet clear what is the natural scope of the acceleration concept. In this paper, we study accelera…
Derives formulas for capital asset performance in continuous time.
problem No stochastic assumptions, no investor beliefs or preferences.
method Game-theoretic approach to efficient market hypothesis.
result Formula resembling classical CAPM for security or portfolio returns.
Paper tackles risk-sensitive impulse control for continuous-time processes.
problem Risk-sensitive impulse control for continuous-time Feller-Markov processes.
method Probabilistic approach to solve Bellman equation and construct optimal strategy.
result Optimal strategy approximated by dyadic impulse strategies.
In this paper, a finite-state mean-reverting model for the short-rate, based on the continuous time Ehrenfest process, will be examined. Two explicit pricing formulae for zero-coupon bonds will be derived in the general and the special symmetric cases. Its limiting relationship to the Vasicek model will be examined wit…
We aim to construct the optimal solutions to the undiscounted continuous-time infinite horizon optimization problems, the objective functionals of which may be unbounded. We identify the condition under which the limit of the solutions to the finite horizon problems is optimal for the infinite horizon problems under th…
Graph neural networks learn PDEs from sparse, irregular data.
problem Learning PDEs from irregularly spaced data.
method Continuous-time differential model with graph neural networks for arbitrary discretizations.
result Efficient inference with continuous-time adjoint method.
We derive the ODE of MAML and propose a new BI-MAML algorithm.
problem Training efficiency and computational burden in MAML.
method Continuous-time limit view of MAML, ODE derivation, and BI-MAML algorithm.
result MAML ODE shows linear convergence rate for strongly convex task losses.
New methods for calculating curvature in graph theory.
problem Calculating curvature in graphs and random walks.
method Analyzing continuous and discrete-time Ollivier-Ricci curvatures of weighted graphs.
result Generalized existence and properties of Ollivier-Ricci curvature for various random walks.
The discrete-time GARCH methodology which has had such a profound influence on the modelling of heteroscedasticity in time series is intuitively well motivated in capturing many `stylized facts' concerning financial series, and is now almost routinely used in a wide range of situations, often including some where the d…
Improved continuous-time consistency models for large-scale image generation.
problem Training instability and discretization errors in existing diffusion models.
method Unified theoretical framework, improved diffusion process, and network architecture.
result Trained continuous-time CMs at 1.5B parameters, achieving state-of-the-art FID scores.
New method decomposes profits and losses continuously, avoiding discrete reporting issues.
problem Analyzing profits and losses at discrete dates ignores detailed paths.
method Constructs a large class of continuous-time decompositions using extended Itô's formula.
result Identifies a preferred decomposition from exactness, symmetry, and normalization axioms.
Proposes a new algorithm for learning continuous-time Bayesian network structures.
problem Lack of constraint-based algorithms for continuous-time Bayesian networks.
method Develops a constraint-based algorithm using statistical tests for conditional independence.
result The proposed algorithm is more accurate with variables having more than two values.
Naive investors make riskier choices than optimal strategies in continuous-time finance.
problem Continuous-time Markowitz portfolio selection with naive reoptimization.
method Analytical derivation of naive policies from discretely naive policies.
result Naive policies are always riskier and less efficient than equilibrium policies.
The paper studies problem of continuous time optimal portfolio selection for a incom- plete market diffusion model. It is shown that, under some mild conditions, near optimal strategies for investors with different performance criteria can be constructed using a limited number of fixed processes (mutual funds), for a m…
Continuous time analysis of momentum methods in neural networks.
problem Understanding the role of momentum in training neural networks.
method Deriving continuous time approximations of discrete algorithms to expose mechanisms.
result Fixed momentum methods approximate a time-rescaled gradient descent flow asymptotically.
Estimates transition rates of continuous-time Markov chains using imprecise probabilistic methods.
problem Estimating transition rate matrix from a finite-duration process.
method Imprecise probabilistic framework with conjugate priors and discrete-time analysis for hyperparameter determination.
result Continuous-time estimator with simple closed-form expression derived from discrete-time model.
In this paper we propose the notion of continuous-time dynamic spectral risk-measure (DSR). Adopting a Poisson random measure setting, we define this class of dynamic coherent risk-measures in terms of certain backward stochastic differential equations. By establishing a functional limit theorem, we show that DSRs may …
We derive a continuous time model for the joint evolution of the mid price and the bid-ask spread from a multiscale analysis of the whole limit order book (LOB) dynamics. We model the LOB as a multiclass queueing system and perform our asymptotic analysis using stylized features observed empirically. We argue that in t…
High Frequency Trading (HFT) represents an ever growing proportion of all financial transactions as most markets have now switched to electronic order book systems. The main goal of the paper is to propose continuous time equations which generalize the self-financing relationships of frictionless markets to electronic …
New algorithm maximizes adoption of multiple products in social networks with limited resources.
problem Maximizing adoption of multiple products in social networks with user attention, budget, and time constraints.
method Formulated as submodular maximization task in continuous-time diffusion model under matroid and multiple knapsack constraints. Proposed randomized algorithm estimating user influence and adaptive threshold greedy algorithm achieving good approximation factor.
result Achieves state-of-the-art effectiveness and scalability in maximizing adoption of multiple products.
Study on LOB dynamics using mean-field game theory.
problem Modeling liquidity dynamics in limit order books.
method Mean-field stochastic differential equation and control problem formulation.
result Equilibrium density function of LOB can be derived.
Continuous-time pricing-hedging duality for European options.
problem Finding the minimal superhedging price of path-dependent European options.
method Formulates a duality between analytic and probabilistic problems, using simple trading strategies and semi-continuous claims.
result The minimal superhedging price equals the supremum of expectations over all martingale measures.
We study an optimal execution problem with uncertain market impact to derive a more realistic market model. We construct a discrete-time model as a value function for optimal execution. Market impact is formulated as the product of a deterministic part increasing with execution volume and a positive stochastic noise pa…
We study the high-frequency limits of strategies and costs in a Nash equilibrium for two agents that are competing to minimize liquidation costs in a discrete-time market impact model with exponentially decaying price impact and quadratic transaction costs of size θ≥0. We show that, for θ=0, equilibrium strategie…
Enhances RL for jump processes using MSBVE algorithm.
problem Challenges in continuous-time RL with jumps and noise.
method Introduces MSBVE algorithm to minimize quadratic variation error.
result MSBVE algorithm outperforms MSTDE in jump processes.
Continuous-time optimal stopping solved with deep reinforcement learning
problem Optimal stopping problems in continuous time
method CARLOS (Continuous-time Adaptive Reinforcement Learning for Optimal Stopping)
result Higher prices than existing Bermudan solvers, approaching American upper bound
Extends reduced-form models to model uncertainty, studying superhedging in continuous time.
problem Model uncertainty in financial markets, particularly credit and insurance.
method Sublinear conditional expectation with respect to a family of probability measures.
result Established equivalent versions of dynamic robust superhedging duality.
Paper solves Bayesian bandit problem with continuous-time limit and approximate policy.
problem Finding optimal policy in Bayesian bandit problems with large horizons.
method Reformulates Bayesian bandit problem as continuous Hamilton-Jacobi-Bellman (HJB) equation and proposes approximate Bayes-optimal policy.
result Approximate Bayes-optimal policy for large horizons with constant computational cost.
ADD-THIN improves TPP forecasting by handling long-term data sequences.
problem Sequential limitations in autoregressive models for TPPs.
method Diffusion model for TPPs that operates on entire sequences.
result ADD-THIN outperforms state-of-the-art models in forecasting.
Improves observation-driven filters using proper scoring rules for better parameter estimation.
problem Improves parameter estimation in observation-driven filters.
method Replaces likelihood score with negative parameter derivative of a proper scoring rule.
result Establishes consistency and asymptotic normality for estimation.
It is well known that mean-variance portfolio selection is a time-inconsistent optimal control problem in the sense that it does not satisfy Bellman's optimality principle and therefore the usual dynamic programming approach fails. We develop a time- consistent formulation of this problem, which is based on a local not…
Continuous time random walks (CTRWs) are used in physics to model anomalous diffusion, by incorporating a random waiting time between particle jumps. In finance, the particle jumps are log-returns and the waiting times measure delay between transactions. These two random variables (log-return and waiting time) are typi…
Researchers find optimal stopping points for assets under non-exponential discounting.
problem Finding optimal stopping points for assets under non-exponential discounting.
method Constructing optimal equilibria for continuous-time stopping problems with specific conditions.
result Optimal equilibria are unique under certain conditions and can be characterized explicitly.
New method uses differential equations for better counterfactual analysis.
problem Estimating counterfactual outcomes for policy analysis.
method Continuous-time approach to synthetic controls using controlled differential equations.
result Improves counterfactual estimation for irregularly aligned multivariate time series.
Study approximates financial market with discrete-time models.
problem Approximating continuous-time financial market models with discrete-time.
method Constructs discrete-time market models with Markov switching and proves convergence.
result Discrete-time models converge to continuous-time Black-Scholes model with Markov switching.
We analyze a tractable model of a limit order book on short time scales, where the dynamics are driven by stochastic fluctuations between supply and demand. We establish the existence of a limiting distribution for the highest bid, and for the lowest ask, where the limiting distributions are confined between two thresh…
New method resolves time order in genetic mutation models.
problem Underspecification in modeling genetic mutation time evolution.
method Continuous-time Markov chains with additional independent items.
result Additional items help determine time order and resolve underspecification.
Paper introduces efficient methods for probabilistic querying of event sequences.
problem Hard queries about future events in continuous-time sequences.
method Importance sampling framework for addressing query types.
result Method is more efficient than naive simulation, often 1,000 times.
Deep-MacroFin uses neural networks to solve complex economic models efficiently.
problem Solving high-dimensional partial differential equations in continuous time economics.
method Leverages deep learning, specifically Multi-Layer Perceptrons and Kolmogorov-Arnold Networks, optimized with HJB equations.
result Offers a more efficient solution (5imes less memory, 40imes fewer FLOPs) for 50D economic models. Analyzes SGD's behavior under heavy-tailed noise, deriving step-size conditions for metastability.
problem Analyzing SGD's performance under heavy-tailed gradient noise.
method Modeling SGD as a discretized SDE driven by Lévy motion, deriving step-size conditions.
result Identifies small step-sizes for discrete system to inherit continuous-time system's metastability behavior.
New method for fluid approximation of CTMCs without population structure.
problem Approximating the macro-scale behavior of large CTMCs.
method Spectral analysis of CTMC transition matrix, diffusion maps, Gaussian process regression.
result Construct an ODE approximating CTMC mean in continuous space.
Faster policy learning via continuous-time gradients.
problem Efficiently estimating policy gradients for continuous-time systems.
method Approximating continuous-time gradients directly, using adaptive discretization.
result More efficient policy gradient estimator leads to faster learning.