Improved gap-dependent bounds for reinforcement learning with linear approximations.
problem Achieving nearly minimax-optimal performance with linear function approximation.
method Developed and analyzed the LSVI-UCB++ algorithm and its concurrent variant.
result First gap-dependent regret bound for nearly minimax-optimal algorithm LSVI-UCB++.
Study on RNNs' ability to approximate past-dependent Hölder functions and their application to regression.
problem Understanding and optimizing the approximation capacity of RNNs for regression tasks.
method Derivation of upper bounds on RNN approximation error for Hölder smooth functions and application to regression.
result Achievement of minimax optimal prediction error bounds for RNNs under various data assumptions.
Paper tackles instance-dependent label noise by approximating it with part-dependent noise.
problem Learning with instance-dependent label noise is challenging.
method Approximate instance-dependent label noise with part-dependent noise. Use transition matrices for parts to model noise.
result Method outperforms state-of-the-art approaches for instance-dependent label noise.
Structured Nonparametric Variational Inference for Dependent Latent Modeling
problem Approximating posterior distributions with complex dependencies among latent variables
method Structured Nonparametric Variational Inference (SN-VI)
result Flexible and accurate posterior approximation with arbitrary shapes
UCRL-WVTR tackles long-term reinforcement learning with general approximations, achieving horizon-free and instance-dependent regret bounds.
problem Long-term reinforcement learning with general function approximations.
method UCRL-WVTR proposes a novel algorithm, UCRL-WVTR, with weighted value-targeted regression and a high-order moment estimator.
result Achieves horizon-free and instance-dependent regret bounds matching minimax lower bounds up to logarithmic factors.
This paper proposes a new method to improve VI approximations by capturing dependence between blocks using vector copulas.
problem Improving variational inference accuracy for complex models with challenging posteriors.
method Using vector copulas to model dependence between multivariate blocks, with learnable transport maps for flexible marginals.
result The proposed method produces more accurate posterior approximations than existing methods at limited computational cost.
Diffusion Transformer captures spatial-temporal dependencies in sequential data.
problem Capturing rich spatial and temporal dependencies in sequential data.
method Established theoretical guarantees for diffusion transformers learning Gaussian process data.
result Spatial-temporal dependencies are captured within attention layers of diffusion transformers.
We consider interactive learning and covering problems, in a setting where actions may incur different costs, depending on the response to the action. We propose a natural greedy algorithm for response-dependent costs. We bound the approximation factor of this greedy algorithm in active learning settings as well as in …
The paper provides an efficient method to price path-dependent derivatives using multiscale stochastic volatility models.
problem Pricing path-dependent derivatives under multiscale stochastic volatility models.
method Derives a Malliavin representation for the first-order approximation of the price of path-dependent derivatives.
result An efficient Monte Carlo approximation for pricing path-dependent derivatives is derived.
In this paper, we give a numerical method for pricing long maturity, path dependent options by using the Markov property for each underlying asset. This enables us to approximate a path dependent option by using some kinds of plain vanillas. We give some examples whose underlying assets behave as some popular Levy proc…
We introduce two versions of a new sketch for approximately embedding the Gaussian kernel into Euclidean inner product space. These work by truncating infinite expansions of the Gaussian kernel, and carefully invoking the RecursiveTensorSketch [Ahle et al. SODA 2020]. After providing concentration and approximation pro…
A method to approximate instance-dependent label noise using instance-confidence embedding.
problem Real-world label noise that depends on individual instances.
method Variational approximation with instance embedding to capture instance-specific label corruption.
result ICE method effectively approximates instance-dependent noise and detects ambiguous instances.
Deep neural nets approximate high-dimensional HJB equations efficiently.
problem Approximating solutions to high-dimensional HJB equations.
method Deep neural networks for approximating solutions.
result Deep neural networks can approximate solutions without the curse of dimensionality.
A new method detects and displays pairwise dependence between variates.
problem Detecting and visualizing dependence between variates of different types.
method Recursive random binning with approximations to Pearson's statistic.
result The method is well-calibrated and powerful against common test alternatives.
Study on coskewness under varying dependence uncertainty.
problem Impact of dependence uncertainty on coskewness.
method Explicit bounds and numerical approximation for product expectation; introduction of standardized rank coskewness.
result Introduced standardized rank coskewness as a measure invariant under transformations.
Papers learn from data to make decisions without interacting, improving on previous methods.
problem Achieving optimal decision-making from offline data with non-linear function approximation.
method Pessimistic Nonlinear Least-Square Value Iteration (PNLSVI) with three innovative components.
result Achieves minimax optimal instance-dependent regret for non-linear function approximation.
Study optimizes solving fixed-point equations using subspace search.
problem Solving linear fixed point equations in Hilbert spaces.
method Linear stochastic approximation scheme with Polyak--Ruppert averaging.
result Established optimal approximation factor for temporal difference learning methods.
Improved semialgebraic choices with linear complexity.
problem Finding semialgebraic choices in projections with exponential complexity.
method Allowing approximate selections in Hausdorff sense.
result Constructed an approximate selection with linear degree in complexity.
Stochastic algo learns from evolving data, achieving optimal performance.
problem Performative prediction and multiplayer extensions.
method Stochastic approximation with decision-dependent distributions.
result Asymptotic normality and optimality of the algorithm's performance.
Framework for universal graph function approximators outperforms existing methods.
problem Graph classification and separation of graph classes.
method Inspired by persistent homology, dependency parsing, and multivalued functions, the framework constructs universal approximators on graph isomorphism classes.
result Achieves state-of-the-art performance on four graph datasets.
Study optimal and instance-dependent guarantees for solving linear equations with Markovian data.
problem Approximately solving linear fixed point equations with Markovian data.
method Non-asymptotic bounds and instance-dependent characterizations for stochastic approximation.
result Instance-optimality of the averaged SA estimator and matching upper and lower bounds.
New algorithm tackles multi-agent reinforcement learning with optimal convergence rate.
problem Multi-agent reinforcement learning with large state spaces and linear function approximations.
method Refined AVLPR framework with data-dependent pessimistic estimation and action-dependent bonuses.
result First algorithm with optimal O(T−1/2) convergence rate and no poly(Amax) dependency. Paper proves GDL models can approximate any continuous function on non-Euclidean data.
problem Processing non-Euclidean data with universal feedforward models.
method Introduces geometric deep learning framework for differentiable manifold geometries.
result GDL models can uniformly approximate any continuous function on compact sets.
SIGMA prior enables federated learning for non-factorizable models.
problem Current FL methods assume conditional independence, limiting applicability to non-factorizable models.
method SIGMA prior approximates deep generative model to induce conditional independence structure.
result SIGMA prior expands FL applicability to fields requiring modeling dependencies.
We investigate the computational aspects of the basket CDS pricing with counterparty risk under a credit contagion model of multinames. This model enables us to capture the systematic volatility increases in the market triggered by a particular bankruptcy. The drawback of this problem is its analytical complication due…
We investigate aspects of semimartingale decompositions, approximation and the martingale representation for multidimensional correlated Markov processes. A new interpretation of the dependence among processes is given using the martingale approach. We show that it is possible to represent, in both continuous and discr…
Transformer networks approximate Hölder and Sobolev functions with fixed-depth networks.
problem Nonparametric regression with dependent observations.
method Established novel upper bounds for Transformer networks approximating Hölder and Sobolev functions under various β-mixing data assumptions. result Explicit convergence rates for nonparametric regression problems under β-mixing data assumptions. Study on SA with heavy-tailed and LRD noise, establishing finite-time bounds.
problem Analyzing stochastic approximation under heavy-tailed and LRD noise.
method Noise-averaging argument to regularize impact of non-classical noise.
result Established first finite-time moment bounds for SA under heavy-tailed and LRD noise.
New method aggregates Gaussian experts by detecting conditional independence violations.
problem Aggregation of dependent Gaussian experts leads to sub-optimal solutions.
method Uses Gaussian graphical model to detect and correct conditional independence violations.
result Improves aggregation of Gaussian experts, outperforming SOTA DGP approaches.
The paper bounds the excess risk of deep neural networks for weakly dependent processes.
problem Learning with weakly dependent data using deep neural networks.
method Approximation of smooth functions by deep neural networks and a bound on excess risk.
result The excess risk bound for deep learning under weak dependence is close to O(n−1/2) for sufficiently smooth functions. New simulation approaches to evaluating path-dependent options without matrix inversion issues nor Euler bias are evaluated. They employ three main contributions: Stochastic approximation replaces regression in the LSM algorithm; Explicit weak solutions to stochastic differential equations are developed and applied to …
Deep networks with path norm regularization can approximate analytic functions.
problem Approximating analytic functions with neural networks.
method Path norm regularized deep networks with activation function.
result Deep networks can approximate analytic functions with logarithmic dependence on approximation error.
Explaining complex or seemingly simple machine learning models is an important practical problem. We want to explain individual predictions from a complex machine learning model by learning simple, interpretable explanations. Shapley values is a game theoretic concept that can be used for this purpose. The Shapley valu…
Improved calibration of HJM models using small volatility approximation.
problem Calibration issues in HJM models with deterministic correlations and mean reversals.
method Use of Small Volatility Approximation in calibration of Multi-Factor HJM models.
result Calibration quality is very good and independent of the number of factors.
One of the central goals of Recurrent Neural Networks (RNNs) is to learn long-term dependencies in sequential data. Nevertheless, the most popular training method, Truncated Backpropagation through Time (TBPTT), categorically forbids learning dependencies beyond the truncation horizon. In contrast, the online training …
Proposes a method to estimate time-dependent probability density functions using binary classifiers.
problem Estimating time-dependent probability density functions of stochastic processes.
method Trains a time-dependent binary classifier to discriminate between realizations of a stochastic process at two nearby time instants.
result Explicitly models and accurately reconstructs complex time-dependent, multi-modal, and near-degenerate densities.
In this paper, we present a Longstaff-Schwartz-type algorithm for optimal stopping time problems based on the Brownian motion filtration. The algorithm is based on Leão, Ohashi and Russo and, in contrast to previous works, our methodology applies to optimal stopping problems for fully non-Markovian and non-semimartinga…
Paper adapts causal analysis for time-dependent systems, especially energy management.
problem Challenges in root-cause analysis for systems with lagged time-dependencies, particularly in energy management.
method Adapts causal root-cause analysis method to time-dependent systems, discusses two truncation approaches.
result Extension effectively localizes root-causes in feature and time domain with enough lags.
Unified view of federated learning and distributed RL using local stochastic approximation.
problem Finding the root of an operator composed of local operators in a network of agents with dependent data.
method Local stochastic approximation over a network of agents with Markov process-dependent data.
result Convergence rates of local stochastic approximation for both constant and time-varying step sizes, within a logarithmic factor of independent data.
New methods improve temporal difference learning for policy evaluation in Markov decision processes.
problem Improving temporal difference learning for policy evaluation in Markov decision processes.
method Introduced variance-reduced forms of stochastic approximation to achieve non-asymptotic, instance-dependent optimality.
result Temporal difference learning is strictly suboptimal, but variance-reduced forms achieve optimality up to logarithmic factors.
Multi-Output Dependence (MOD) learning is a generalization of standard classification problems that allows for multiple outputs that are dependent on each other. A primary issue that arises in the context of MOD learning is that for any given input pattern there can be multiple correct output patterns. This changes the…
The paper shows how neural networks can approximate PDEs with polynomial scaling in dimension.
problem Understanding the complexity of approximating PDE solutions with neural networks.
method Developed a proof technique to simulate gradient descent using neural networks.
result Neural network parameters scale polynomially with input dimension for approximating PDE solutions.
This paper investigates the approximation power of three types of random neural networks: (a) infinite width networks, with weights following an arbitrary distribution; (b) finite width networks obtained by subsampling the preceding infinite width networks; (c) finite width networks obtained by starting with standard G…
In this paper, we propose a generic framework for devising an adaptive approximation scheme for value function approximation in reinforcement learning, which introduces multiscale approximation. The two basic ingredients are multiresolution analysis as well as tree approximation. Starting from simple refinable function…
CSD improves goodness-of-fit testing for higher-order dependence.
problem Insensitivity of standard KSDs to higher-order dependence features like tail dependence.
method Introduces Copula-Stein Discrepancy (CSD) that targets dependence geometry directly on copula density.
result CSD is sensitive to differences in tail dependence coefficients and metrizes weak convergence of copula distributions.
McDiarmid's inequality under dependence via approximate tensorization of entropy
problem Dependent versions of McDiarmid's inequality
method Approximate tensorization of entropy (ATE)
result Derives McDiarmid's inequality for non-isotropic Gaussian random vectors
We analyze analytic approximation formulae for pricing zero-coupon bonds in the case when the short-term interest rate is driven by a one-factor mean-reverting process with a volatility nonlinearly depending on the interest rate itself. We derive the order of accuracy of the analytical approximation due to Choi and Wir…
We develop a general variational inference method that preserves dependency among the latent variables. Our method uses copulas to augment the families of distributions used in mean-field and structured approximations. Copulas model the dependency that is not captured by the original variational distribution, and thus …