Proves convergence of neural networks in a two-timescale regime.
problem Training dynamics of shallow neural networks.
method Two-timescale regime analysis of gradient flow.
result Gradient flow converges to global optimum in non-convex optimization.
Paper analyzes normal approximation for two-timescale stochastic algorithms, revealing interaction between fast and slow timescales.
problem Non-asymptotic bounds for accuracy of normal approximation in linear two-timescale stochastic approximation algorithms.
method Established bounds for normal approximation in terms of convex distance, focusing on last iterate and Polyak-Ruppert averaging.
result Normal approximation rate for the last iterate improves with increased timescale separation, while it decreases in the averaged setting.
In this paper we present a framework to analyze the asymptotic behavior of two timescale stochastic approximation algorithms including those with set-valued mean fields. This paper builds on the works of Borkar and Perkins & Leslie. The framework presented herein is more general as compared to the synchronous two times…
This study improves convergence of two-timescale SA under Markovian noise in reinforcement learning.
problem Stability and convergence of two-timescale stochastic approximations under Markovian noise.
method Introduced a new control strategy for the fast timescale parameter.
result Established almost sure convergence of TDC with eligibility traces under off-policy learning with linear function approximation.
Paper analyzes Greedy-GQ for reinforcement learning with Markovian noise.
problem Analyzing Greedy-GQ for reinforcement learning with Markovian noise.
method Develops finite-sample analysis for Greedy-GQ with linear function approximation under Markovian noise.
result Provides theoretical justification for choosing stepsizes for faster convergence.
This paper analyzes the sample complexity of two timescale reinforcement learning algorithms.
problem Analyzing the sample complexity of two timescale reinforcement learning algorithms.
method Non-asymptotic analysis of linear and nonlinear TDC and Greedy-GQ algorithms under Markovian sampling with constant stepsize.
result The paper provides non-asymptotic convergence results for two timescale linear and nonlinear TDC and Greedy-GQ algorithms.
Paper analyzes finite-time performance of SA in RL with Markovian noise.
problem Finite-time analysis of linear two-timescale stochastic approximation with Markovian noise.
method Finite-time analysis of linear two-timescale SA with Markovian noise, considering both transient and steady-state terms.
result No discrepancy in convergence rate between Markovian and martingale noise; transient term is o(1/kc) and steady-state term is O(1/k). This work analyzes how neural networks learn representations in actor-critic algorithms.
problem Theoretical support for neural AC algorithms is limited to linear function approximations.
method Mean-field analysis of a two-timescale learning AC algorithm with overparameterized networks.
result Neural AC finds the globally optimal policy at a sublinear rate in the continuous-time and infinite-width limiting regime.
Study on Adam-family methods for nonsmooth optimization with convergence guarantees.
problem Training nonsmooth neural networks with convergence guarantees.
method Two-timescale updating scheme and stochastic subgradient methods with gradient clipping.
result Convergence guarantees for various Adam-family methods in training nonsmooth neural networks.
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.
We present the first provably convergent two-timescale off-policy actor-critic algorithm (COF-PAC) with function approximation. Key to COF-PAC is the introduction of a new critic, the emphasis critic, which is trained via Gradient Emphasis Learning (GEM), a novel combination of the key ideas of Gradient Temporal Differ…
Two-Timescale EM Methods improve EM for nonconvex models.
problem Nonconvex latent variable models are challenging for EM.
method Two-stage stochastic updates to handle nonconvex optimization.
result Global convergence for nonconvex objective functions.
Study Whittle index learning algorithms for restless bandits with constant stepsizes.
problem Optimizing decisions in restless multi-armed bandits with constant stepsizes.
method Developed Q-learning algorithms with constant stepsizes for index learning in restless bandits, extending to DQN and function approximations.
result The algorithms learn the Whittle index effectively.
Paper analyzes CLT for TTSA with Markovian noise, broadening its applications.
problem Analyzing asymptotic behavior of TTSA under Markovian noise.
method Central Limit Theorem applied to TTSA with Markovian noise.
result Uncovered coupled dynamics of TTSA influenced by Markov chain.
Authors improve accuracy analysis for portfolio optimization with multiple timescale factors.
problem Asymptotic accuracy of portfolio optimization approximations for general utility functions and two timescale factors.
method Construct sub- and super-solutions to fully nonlinear problem.
result Rigorous justification of accuracy for portfolio optimization with general utility functions and two timescale factors.
Two-layer neural networks learn efficiently using kernel methods in mean-field analysis.
problem Feature learning ability of two-layer neural networks in the mean-field regime.
method Mean-field analysis through kernel methods, focusing on dynamics of the first layer's kernel.
result Two-layer neural networks can learn a union of multiple reproducing kernel Hilbert spaces more efficiently than kernel methods.
The paper analyzes the sample complexities for policy evaluation with linear function approximation.
problem Policy evaluation with linear function approximation in discounted infinite horizon Markov decision processes.
method Investigates sample complexities for two policy evaluation algorithms: TD and TDC.
result Establishes high-probability sample complexity bounds for policy evaluation algorithms.
New learning rate approach reveals phase transitions in SGD performance.
problem Understanding feature learning dynamics in neural networks.
method Characterizing the relationship between learning rate(s) and sample complexity for gradient-based algorithms.
result Phase transition from information exponent to generative exponent regime with different learning rates.
We present for the first time an asymptotic convergence analysis of two time-scale stochastic approximation driven by `controlled' Markov noise. In particular, both the faster and slower recursions have non-additive controlled Markov noise components in addition to martingale difference noise. We analyze the asymptotic…
The asymptotic pseudo-trajectory approach to stochastic approximation of Benaim, Hofbauer and Sorin is extended for asynchronous stochastic approximations with a set-valued mean field. The asynchronicity of the process is incorporated into the mean field to produce convergence results which remain similar to those of a…
We propose local symplectic surgery, a two-timescale procedure for finding local Nash equilibria in two-player zero-sum games. We first show that previous gradient-based algorithms cannot guarantee convergence to local Nash equilibria due to the existence of non-Nash stationary points. By taking advantage of the differ…
Motivated by the recent applications of game-theoretical learning techniques to the design of distributed control systems, we study a class of control problems that can be formulated as potential games with continuous action sets, and we propose an actor-critic reinforcement learning algorithm that provably converges t…
New analysis improves understanding of bilevel optimization stability and generalization.
problem Understanding how well bilevel optimization algorithms generalize.
method Algorithmic stability arguments and generalization bounds for three bilevel minimax solvers.
result Precise trade-off between algorithmic stability, generalization gaps, and practical settings.
New IRL algorithm identifies optimal reward and policy from expert demonstrations.
problem Understanding reward functions from expert demonstrations with neural networks.
method Two-timescale single-loop IRL algorithm for neural network parameterized rewards.
result First IRL algorithm with non-asymptotic convergence guarantee and global optimality in neural network settings.
Two novel algorithms improve distributed machine learning in the presence of Byzantine adversaries.
problem Improving distributed machine learning in the presence of Byzantine adversaries.
method Two novel stochastic gradient descent algorithms, ByGARS and ByGARS++, using reputation scores for gradient aggregation.
result Robust to any number of multiplicative noise Byzantine adversaries and converge for strongly convex loss functions.
The paper analyzes an actor-critic algorithm with target networks for deep reinforcement learning.
problem Lack of theoretical understanding of target networks in actor-critic methods.
method Proposes a theoretical analysis of an online target-based actor-critic algorithm with linear function approximation.
result Establishes asymptotic convergence results and finite-time analysis for both critic and actor.
Study best-response learning dynamics in zero-sum polymatrix games under full and minimal information settings.
problem Learning dynamics in zero-sum polymatrix games under different information settings.
method Two-timescale learning dynamics combining smoothed best-response updates and TD-learning for estimating local payoff functions.
result Polynomial-time finite-sample guarantees for convergence to an ε-Nash equilibrium in the minimal information case.
Study improves distributed linear estimation under adversarial conditions.
problem Mean estimation of a random vector with adversarial measurements and asynchrony.
method Two-timescale ℓ1-minimization algorithm with tight convergence rates.
result Unified finite-time characterization of robustness, identifiability, and statistical efficiency.
Paper analyzes Transformer learning dynamics, proving benign landscape for in-context learning.
problem Understanding how Transformers learn in context with nonlinear features.
method Mean-field and two-timescale analysis of Transformer dynamics, proving nonconvex but benign landscape.
result Proves mean-field dynamics avoid saddle points, leading to improved optimization.
Gradient flow solves multi-index regression for high-dimensional Gaussian data.
problem Learning multi-index functions from high-dimensional Gaussian data.
method Two-timescale algorithm with non-parametric link function learning.
result Global convergence of Grassmannian population gradient flow dynamics.
The article detects market regimes from covariance matrices using VLSTAR and clustering models.
problem Market regime switching is hard to detect due to time-varying correlation coefficients.
method The article applies VLSTAR and unsupervised hierarchical clustering on monthly realized covariance matrices.
result VLSTAR outperforms clustering in detecting market regimes.
The study identifies and analyzes different market regimes in equity markets using advanced signal processing techniques.
problem Understanding and quantifying the dynamics of different market regimes in equity markets.
method Data-driven Hilbert--Huang Transform for regime identification, Holo--Hilbert Spectral Analysis for profiling, and Variable-Length Markov Chains for return dynamics modeling.
result Developed markets normalize more effectively as stress subsides, while developing markets retain residual tail dependence and downside persistence.
Develops a new method for efficient stochastic bilevel optimization.
problem Stochastic bilevel optimization problems in machine learning applications.
method Single-Timescale stochAstic BiLevEl optimization (STABLE) method.
result Achieves the same order of sample complexity as stochastic gradient descent for single-level optimization.
Paper improves asset allocation using machine learning for regime detection.
problem Improving asset allocation strategies in uncertain economic conditions.
method Machine learning for regime detection, modified k-means algorithm, portfolio optimization.
result Significant portfolio performance improvements over traditional benchmarks.
Proposes methods for learning optimal dynamic treatment regimes robust to unconfoundedness violations.
problem Estimating optimal dynamic treatment regimes using historical observational data when unconfoundedness is violated.
method Utilizes proximal causal inference framework to propose three nonparametric identification methods, a (K+1)-robust method, and establish a semiparametric efficiency bound.
result Establishes the (K+1)-robust method for learning optimal dynamic treatment regimes, validating its efficiency and multiple robustness through numerical experiments.
New model identifies regimes in non-stationary data.
problem Identifying latent regimes in non-stationary systems with instantaneous effects.
method Identifiable Markov Switching Models with exponential family noise.
result Established identifiability of latent regimes and causal structures.
Single-timescale actor-critic finds globally optimal policy.
problem Finding globally optimal policy in reinforcement learning.
method Simultaneous actor and critic updates with linear or deep neural network approximations.
result Actor sequence converges to globally optimal policy at O(K−1/2) rate. Markov regime switching models have been used in numerous empirical studies in economics and finance. However, the asymptotic distribution of the likelihood ratio test statistic for testing the number of regimes in Markov regime switching models has been an unresolved problem. This paper derives the asymptotic distribu…
Algorithm classifies market regimes using time series signatures.
problem Classifying different market conditions from time series data.
method Utilizes path signatures and a metric structure for clustering.
result Established a connection between regime separation and point clustering.
RegimeFolio optimizes portfolios by adapting to changing market regimes.
problem Non-stationary markets with shifting volatility regimes.
method Explicitly models volatility regimes with sector-specific ensemble forecasting and adaptive mean-variance allocation.
result Significant improvement in return and robustness compared to conventional methods.
Paper addresses uncertainty in model generalization under regime shifts.
problem Uncertainty in model generalization under regime changes.
method Proposes a framework to quantify and separate regime mismatch and sensitivity.
result Obtains exact decomposition and minimax lower bound for regime-aware models.
Enhances portfolio construction with tailored regime forecasts for individual assets.
problem Traditional portfolio construction methods fail to account for asset-specific market conditions.
method Hybrid framework combining unsupervised and supervised learning for regime identification and forecasting.
result Outperforms traditional portfolio models across various asset classes.
In order to obtain a reasonable and reliable forecast method for crude oil price volatility, this paper evaluates the forecast performance of single-regime GARCH models (including the standard linear GARCH model and the nonlinear GJR-GARCH and EGARCH models) and the two-regime Markov Regime Switching GARCH (MRS-GARCH) …
Unified formula for training dynamics of linear networks combining lazy and balanced regimes.
problem Training dynamics of linear networks in two distinct setups: lazy and balanced/active.
method Unified formula for the evolution of the learned matrix, combining lazy and balanced regimes.
result Unified formula allows for rapid convergence and low rank bias, proving a complete phase diagram.
RAMBO optimizes multi-regime problems by discovering and modeling distinct energy basins.
problem Multi-regime problems in molecular conformation and drug discovery.
method Dirichlet Process Mixture of Gaussian Processes with adaptive hyperparameters and concentration parameters.
result Consistent improvements over state-of-the-art on multi-regime objectives.
This paper improves risk control for financial markets by calibrating VaR forecasts using conformal methods.
problem Nonstationary and regime-dependent losses in financial markets.
method Regime-weighted conformal risk control (RWC) for VaR forecasting.
result RWC improves regime-conditional stability in some settings with modest conservativeness changes.
ReCAP adapts to dynamic financial markets by segmenting and combining policy vectors.
problem Inefficient traditional PM approaches in non-stationary financial markets.
method Integrates continual learning into PM, segmenting regimes and adapting policies.
result Consistently outperforms baselines in real-world financial datasets.
New algorithms improve sampling from complex distributions.
problem Sampling from complex probability distributions efficiently.
method Regime-switching Langevin dynamics and Monte Carlo algorithms.
result Convergence guarantees and iteration complexities provided.