DiffATD efficiently discovers targets in partially observable environments using diffusion dynamics.
problem Efficiently discovering targets in partially observable environments with limited sampling.
method DiffATD uses diffusion dynamics to maintain a belief distribution over unobserved states, balancing exploration and exploitation.
result DiffATD outperforms baselines and supervised methods in diverse domains.
HySRL improves RL sample efficiency with shifted-dynamics data.
problem Leveraging historical data with shifted dynamics to improve sample efficiency in RL.
method HySRL, a hybrid transfer RL algorithm that uses prior information on dynamics shift to achieve better sample complexity.
result HySRL achieves problem-dependent sample complexity and outperforms pure online RL.
Proposes a method to improve few-shot transfer in off-dynamics RL.
problem Traditional RL struggles with transferring policies between environments with different dynamics.
method Introduces a penalty to regulate source-trained policies in target environments with limited data.
result Improves performance in various off-dynamics RL scenarios compared to existing methods.
Dynamic rule-based investment strategies outperform static ones in pension schemes.
problem Managing retirement income with dynamic investment strategies.
method Rule-based investment strategies compared to dynamic programming.
result Rule-based strategies achieve higher probability of meeting retirement income targets.
Trained recurrent networks are powerful tools for modeling dynamic neural computations. We present a target-based method for modifying the full connectivity matrix of a recurrent network to train it to perform tasks involving temporally complex input/output transformations. The method introduces a second network during…
Paper proposes methods to reduce financial contagion by targeted cash injections.
problem Financial contagion through interconnected networks.
method Dynamic model of payments with external control term for corrective cash injections.
result Targeted cash injections can significantly reduce default propagation.
Model predicts trading strategies based on latent demand and price impact.
problem Predicting strategic trading behavior of investors with private targets.
method Equilibrium model of dynamic trading, learning, and pricing by strategic investors.
result Trading strategies are a combination of target following, liquidity provision, and front-running based on latent demand and price pressure.
RL policy tracks dynamic targets in partially known environments robustly.
problem Active target tracking in partially known environments.
method Deep reinforcement learning (RL) approach for in-sight tracking, navigation, and exploration.
result Unified RL policy shows robust behavior for agile and anomalous targets.
A new method reformulates Optimal Transport Conditional Flow Matching using proximal operators.
problem Optimal Transport Conditional Flow Matching (OT-CFM) for generating models.
method Reformulate OT-CFM using proximal operators and extended Brenier potential.
result OT-CFM dynamics are terminally normally hyperbolic for manifold-supported targets.
New methods use transport maps to improve Langevin dynamics for sampling.
problem Sampling high-dimensional, non-Gaussian distributions efficiently.
method Apply transport maps to accelerate Langevin dynamics convergence.
result Discretized processes converge to target distribution with non-asymptotic bounds.
AIS uses a suboptimal extended target distribution, which this paper improves using SGM.
problem Improving the efficiency of Annealed Importance Sampling for marginal likelihood estimation.
method Leveraging score-based generative modeling to approximate the optimal extended target distribution.
result Demonstrated novel, differentiable AIS procedures on synthetic and real-world data.
This work analyzes how often to update the target network in Q-learning.
problem Understanding the optimal frequency of target network updates in Q-learning.
method Formulated target updates as a nested optimization scheme, derived finite-time convergence analysis.
result Optimal target update frequency increases geometrically over time.
A new method combines predictors and their lags using supervised PCA for dynamic forecasting.
problem Dynamic forecasting with many predictors.
method Supervised PCA with re-scaling and penalized methods.
result The method outperforms traditional PCA and diffusion-index approaches in prediction.
Enhances RL in target domains with limited data using augmented return.
problem Utilize data from an accessible source domain to improve policy learning in a target domain with scarce data.
method Return Augmented Decision Transformer (REAG) method, which augments the return in the source domain to align with the target domain's optimal trajectory distribution.
result The proposed REAG method achieves the same level of suboptimality as without a dynamics shift, enhancing DT type frameworks' performance in off-dynamics RL.
Unified approach for sampling non-differentiable and heavy-tailed targets.
problem Sampling non-differentiable and heavy-tailed distributions using Langevin algorithms.
method Anchored Langevin dynamics, which modifies the Langevin diffusion with a smooth reference potential and multiplicative scaling.
result Non-asymptotic guarantees in the 2-Wasserstein distance to the target distribution.
Method learns dynamics from sparse, irregular feature data.
problem Learn system dynamics from sparse, irregularly sampled feature time series.
method Formulates as high-dimensional linear regression using signatures.
result Oracle bound on prediction error with explicit sampling dependencies.
This paper improves sampling from complex distributions using Langevin dynamics.
problem Pathological behaviors in normalizing flows for complex distributions.
method A Metropolis adjusted Langevin algorithm (MALA) to sample in the latent space.
result The method preserves tractability of the likelihood and works with any pre-trained NF network.
This paper investigates the equilibrium interactions between trading targets and private information in a multi-period Kyle (1985) market. There are two investors who each follow dynamic trading strategies: A strategic portfolio rebalancer who engages in order splitting to reach a cumulative trading target and an uncon…
Policy-gradient method controls multiple non-cohesive targets.
problem Controlling multiple non-cohesive targets in a decentralized manner.
method Proximal Policy Optimization for target selection and driving.
result Effective control of non-cohesive targets without prior dynamics knowledge.
A new method for reinforcement learning that adapts to different domains using auxiliary classifiers.
problem Training reinforcement learning agents to perform well in different domains with varying dynamics.
method Learning auxiliary classifiers to distinguish source-domain from target-domain transitions and modifying the reward function accordingly.
result The approach improves transfer performance in reinforcement learning tasks with varying dynamics.
This paper analyzes how periodic and soft target updates stabilize linear Q-learning.
problem Theoretical explanation of stabilization mechanisms for linear Q-learning.
method Exact analysis using switched linear system dynamics and the joint spectral radius.
result Periodic and soft target updates can guarantee convergence to the exact projected Q-Bellman solution under specific conditions.
The paper evaluates the probability distributions of analog-to-target distances for multiple analogs.
problem Understanding the performance of analog applications through the distribution of distances to target states.
method Theoretical analysis and numerical experiments using dynamical systems theory.
result The size of the catalog and dimensionality affect the probability distributions of the K-best analogs.
This work introduces a new method for coupling base and target densities in generative models.
problem Generating samples from complex target distributions using simple base distributions.
method Developed a framework of stochastic interpolants with data-dependent couplings.
result Constructing dynamical transport maps that serve as conditional generative models.
Paper compares machine learning methods for predicting target motion.
problem Challenges in accurately modeling target dynamics due to mismatch between assumed and true motion.
method Three machine learning methods (GPs, IMM, LSTM) compared against EKF.
result LSTM network outperforms other methods in real-world scenarios.
BM2 learns Schrödinger bridges using neural networks.
problem Learning dynamic transport maps between two distributions.
method Coupled Bridge Matching (BM2) with neural networks. result Preliminary theoretical analysis and numerical experiments show BM2's effectiveness. ESNs trained with Tikhonov least squares approximate ergodic dynamical systems in L2(μ) norm.
problem Approximating ergodic dynamical systems using ESNs.
method Tikhonov least squares regression on ESNs trained on observations from an ergodic dynamical system.
result ESNs trained with Tikhonov least squares approximate the target function in the L2(μ) norm.
We study a stochastic game where one player tries to find a strategy such that the state process reaches a target of controlled-loss-type, no matter which action is chosen by the other player. We provide, in a general setup, a relaxed geometric dynamic programming principle for this problem and derive, for the case of …
Geometric tempering fails for Langevin dynamics, proving convergence limits.
problem Proving convergence and limitations of geometric tempering for Langevin dynamics.
method Theoretical investigation of geometric tempering using Langevin dynamics.
result Geometric tempering can lead to exponential time convergence and poor functional inequalities.
Proposes Deep LTMLE for estimating dynamic treatment effects in longitudinal studies.
problem Estimating counterfactual mean outcomes under dynamic treatment policies in longitudinal settings.
method Uses a transformer architecture with temporal-difference learning for initial estimation, followed by TMLE correction and statistical inference.
result Demonstrates superior performance in complex, long-term scenarios compared to existing methods.
Paper proposes SDDP for improving time series forecasting with high-dimensional predictors.
problem Improving time series forecasting with high-dimensional predictors.
method SDDP framework that incorporates target variable and lagged observations into factor extraction process.
result SDDP improves predictive accuracy in time series forecasting.
Gaussian-SVGD dynamics converge to Gaussian distributions under certain conditions.
problem Understanding the theoretical properties of SVGD, especially for Gaussian targets.
method Detailed theoretical study of Gaussian-SVGD dynamics, considering both mean-field PDE and discrete particle systems.
result Gaussian-SVGD dynamics converge linearly to the Gaussian distribution closest to the target in KL divergence.
This paper addresses tracking of a moving target in a multi-agent network. The target follows a linear dynamics corrupted by an adversarial noise, i.e., the noise is not generated from a statistical distribution. The location of the target at each time induces a global time-varying loss function, and the global loss is…
New framework embeds generalization in learning dynamics using large deviation theory.
problem Improving generalization and robustness in learning problems.
method Gradient methods from continuous-time perspective with Freidlin-Wentzell theory of large deviations.
result Asymptotic probability estimate for rare events in learning dynamics.
Dynamic treatment strategies on networks amplify policy impact through spillovers.
problem Effective dynamic treatment allocation in network settings.
method Q-Ising, a three-stage pipeline integrating Bayesian dynamic Ising model, treatment adoption histories, and offline reinforcement learning.
result Adaptive targeting outperforms static centrality benchmarks in Indian village microfinance networks and synthetic data.
RL approach for target tracking with unknown dynamics and sensor control.
problem Tracking an unknown target with sensor control.
method Track-MDP formulation for RL, compared with POMDP.
result Optimal RL policy tracks all target paths with certainty.
Analyzes SGD dynamics in two-layer networks, bridging different regimes.
problem Understanding SGD dynamics in high-dimensional and mean-field settings.
method Rigorous analysis via deterministic low-dimensional description of sufficient statistics.
result Infinite-width dynamics remains close to a low-dimensional subspace.
Leveraged ETFs can outperform their targets in certain market conditions, contrary to the volatility drag hypothesis.
problem The long-term performance decay of leveraged ETFs due to volatility drag.
method Unified framework incorporating AR(1) and AR-GARCH models, continuous-time regime switching, and flexible rebalancing frequencies.
result Return dynamics, including return autocorrelation, volatility clustering, and regime persistence, determine LETF performance.
The paper analyzes convergence of Langevin dynamics with time-dependent metrics.
problem Analyzing convergence of Langevin dynamics with time-dependent metrics.
method Formulated a modified gradient flow of the Kullback-Leibler divergence, selected a time-dependent relative Fisher information functional, and developed a time-dependent Hessian matrix condition.
result Proved convergence conditions for various Langevin dynamics.
Paper analyzes Annealed Langevin Dynamics for multimodal sampling stability.
problem Ensuring stability of Annealed Langevin Dynamics across dimensions.
method Uniform-in-dimension analysis of ALD for Gaussian-mixture targets.
result ALD achieves prescribed accuracy in KL divergence with spectral conditions.
Flow AIS Bootstrap improves flow training by generating samples in hard-to-reach regions.
problem Training flows with high variance and mode-seeking behavior.
method Augment flows with AIS and minimize α-divergence with α=2. result FAB learns Boltzmann distribution of alanine dipeptide without MD samples.
StrGNN detects anomalies in dynamic graphs by analyzing subgraphs and temporal features.
problem Detecting anomalies in dynamic graphs with structural changes.
method StrGNN is an end-to-end model that uses structural subgraphs and temporal features for anomaly detection.
result StrGNN effectively detects anomalies in dynamic graphs, as shown by extensive experiments.
New method models complex dynamics using a base variable.
problem Modeling complex high-frequency dynamics from time series.
method Constructing a joint model with a base variable and a target variable.
result Successfully models chaotic behavior and reconstructs statistical properties.
Two-layer networks learn faster with batch reuse, overcoming information and leap exponents.
problem Limitations of gradient flow and single-pass GD in learning multi-index target functions.
method Multi-pass gradient descent that reuses batches, analyzed using Dynamical Mean-Field Theory.
result Two-time-step overlap with target subspace for non-staircase functions, overcoming information and leap exponents.
The challenge in controlling stochastic systems in which low-probability events can set the system on catastrophic trajectories is to develop a robust ability to respond to such events without significantly compromising the optimality of the baseline control policy. This paper presents CelluDose, a stochastic simulatio…
Transfer reinforcement learning (RL) aims at improving the learning efficiency of an agent by exploiting knowledge from other source agents trained on relevant tasks. However, it remains challenging to transfer knowledge between different environmental dynamics without having access to the source environments. In this …
EI-MTD defends edge intelligence against adversarial attacks with dynamic scheduling.
problem Adversarial attacks on edge intelligence models.
method EI-MTD uses differential knowledge distillation to create robust member models and a dynamic scheduling policy based on a Bayesian Stackelberg game.
result EI-MTD effectively protects edge intelligence from black-box adversarial attacks.
Proposes a new method for sampling from unknown distributions.
problem Challenges in sampling from distributions without direct sampling.
method Uses a dilation path to estimate score vectors in closed-form, guiding Langevin dynamics.
result Demonstrates improved sampling performance compared to classical methods.
Langevin dynamics fails to produce accurate samples even with small score function errors.
problem Robustness of Langevin dynamics to score function errors.
method Analysis of Langevin dynamics and score function errors.
result Langevin dynamics produces a distribution far from the target distribution in TV distance even with small L2 errors in the score function.