FVI method calculates bicausal OT with neural networks, outperforming other methods.
problem Computing bicausal optimal transport with adapted coupling structures.
method FVI method using multilayer neural networks to approximate value functions.
result FVI method outperforms linear programming and Sinkhorn methods in scalability.
We present the use of the fitted Q iteration in algorithmic trading. We show that the fitted Q iteration helps alleviate the dimension problem that the basic Q-learning algorithm faces in application to trading. Furthermore, we introduce a procedure including model fitting and data simulation to enrich training data as…
We propose a method for efficient training of Q-functions for continuous-state Markov Decision Processes (MDPs) such that the traces of the resulting policies satisfy a given Linear Temporal Logic (LTL) property. LTL, a modal logic, can express a wide range of time-dependent logical properties (including "safety") that…
A new method calibrates value predictions in offline RL to improve reliability.
problem Difficulty in long-horizon value prediction in offline reinforcement learning.
method Bellman calibration, a weak reliability criterion, and Iterated Bellman Calibration.
result Finite-sample guarantees show that Bellman calibration error is controlled at nonparametric rates.
VA-OPE improves OPE by incorporating variance information, achieving tighter error bounds.
problem Estimating value function of a target policy from offline data collected by a behavior policy.
method Proposes VA-OPE, an algorithm that reweights Bellman residual using estimated variance of the value function.
result Achieves a tighter error bound than the best-known result.
Optimal unimodal fitting for linear loss functions in a sequential, efficient manner.
problem Optimal unimodal transformation of univariate model scores under linear loss functions.
method Proposes a sequential approach to estimate the optimal rectangular fit for observed samples with each new sample.
result Sequential approach achieves optimal efficiency with logarithmic time complexity per iteration.
Kernel Multigrid accelerates Back-fitting for additive Gaussian Processes.
problem Slow convergence of Back-fitting in training additive Gaussian Processes.
method Kernel Packets (KP) and Sparse Gaussian Process Regression (GPR) to enhance Back-fitting.
result Kernel Multigrid reduces the required iterations to O(logn). Iterative algorithms, like gradient descent, are common tools for solving a variety of problems, such as model fitting. For this reason, there is interest in creating differentially private versions of them. However, their conversion to differentially private algorithms is often naive. For instance, a fixed number of i…
A new algorithm reconstructs population dynamics from coarse samples.
problem Reconstructing population dynamics from unlabeled samples at coarse time intervals.
method Deep Momentum Multi-Marginal Schrödinger Bridge (DMSB) framework.
result Significantly outperforms baselines in synthetic and real-world datasets.
Paper provides exponential convergence guarantees for Iterative Markovian Fitting.
problem Addressing the Schrödinger Bridge problem in computational optimal transport and generative modeling.
method Develops non-asymptotic exponential convergence guarantees for Iterative Markovian Fitting.
result First non-asymptotic exponential convergence guarantees for IMF under mild structural assumptions.
Stability result for a popular algorithm in optimal transport.
problem Stability of the Iterative Proportional Fitting Procedure in time and metric.
method Uniform stability analysis in the 1-Wasserstein metric.
result Quantitative stability result for entropy-regularized Optimal Transport and Schrödinger bridges.
New method improves stability of soft FQI for offline RL.
problem Stability issues in soft FQI under function approximation.
method Stationary reweighting to align operator norms.
result Local linear convergence proved under certain conditions.
New insights into using IPF for inferring dynamic networks from marginals.
problem Inferring dynamic networks from time-aggregated adjacency matrices and time-varying marginals.
method Identifying a generative network model and establishing its maximum likelihood estimates via IPF, with convergence guarantees for sparse data.
result IPF provides principled estimation of dynamic networks from marginals under certain conditions, with structure-dependent error bounds and guaranteed convergence for sparse data.
A fast method estimates Gaussian mixture components without iterative fitting.
problem Estimating the number of components in high-dimensional Gaussian mixtures.
method Center data, compute singular values, and count above a threshold.
result The estimator consistently recovers the true number of components under mild separation condition.
Develops fast approximations for conditional Shapley values in linear and polynomial models.
problem Estimating conditional Shapley values using regression models is computationally expensive.
method A new approximative estimation method for conditional Shapley values using linear and polynomial regression models.
result Our method significantly reduces computation time compared to existing methods.
FORE evaluates occupancy ratios without requiring Bellman completeness.
problem Offline reinforcement learning occupancy ratio estimation.
method Fitted occupancy-ratio evaluation (FORE) using adjoint Bellman recursion.
result FORE achieves convergence in KL without Bellman completeness.
Self-distillation improves model performance but can lead to underfitting.
problem Understanding why self-distillation improves model performance and its limitations.
method Theoretical analysis of self-distillation in Hilbert space with ℓ2 regularization. result Self-distillation modifies regularization by limiting the number of basis functions, potentially leading to underfitting.
Wasserstein gradient boosting predicts probability distributions for supervised learning.
problem Distribution-valued supervised learning where outputs are probability distributions.
method Fits a new weak learner to Wasserstein gradients of loss functionals of probability distributions.
result Superior performance in probabilistic prediction compared to existing methods.
Support vector machines (SVMs) are an important tool in modern data analysis. Traditionally, support vector machines have been fitted via quadratic programming, either using purpose-built or off-the-shelf algorithms. We present an alternative approach to SVM fitting via the majorization--minimization (MM) paradigm. Alg…
Gaussian processes (GPs) with derivatives are useful in many applications, including Bayesian optimization, implicit surface reconstruction, and terrain reconstruction. Fitting a GP to function values and derivatives at n points in d dimensions requires linear solves and log determinants with an ${n(d+1) \times n(d…
Ancestral graph models, introduced by Richardson and Spirtes (2002), generalize both Markov random fields and Bayesian networks to a class of graphs with a global Markov property that is closed under conditioning and marginalization. By design, ancestral graphs encode precisely the conditional independence structures t…
New RL algorithm explains why deep learning works in stochastic environments.
problem Why deep RL algorithms perform well in practice despite using random exploration.
method Introducing SQIRL, an iterative RL algorithm that separates exploration and learning.
result Effective horizon explains why deep RL works in stochastic environments.
A new algorithm solves signed Fréchet regression on manifolds with bounded curvature.
problem Signed Fréchet regression on Riemannian manifolds with bounded curvature.
method Proximal DC algorithm (FRIDA) for computing signed Fréchet regression fits.
result Existence and interiority of minimizers, strong convexity of proximal subproblems, and convergence to stationary points.
Paper proposes FPG algorithm for unbiased off-policy PG estimation.
problem Challenges in off-policy policy gradient estimation.
method Double Fitted PG estimation (FPG) algorithm for arbitrary policy parameterization.
result Empirically, FPG significantly outperforms existing methods.
The goal of dynamic time warping is to transform or warp time in order to approximately align two signals together. We pose the choice of warping function as an optimization problem with several terms in the objective. The first term measures the misalignment of the time-warped signals. Two additional regularization te…
Subset selection in multiple linear regression aims to choose a subset of candidate explanatory variables that tradeoff fitting error (explanatory power) and model complexity (number of variables selected). We build mathematical programming models for regression subset selection based on mean square and absolute errors…
The paper explores when and why value decomposition algorithms work in cooperative multi-agent reinforcement learning.
problem The applicability and convergence properties of value decomposition algorithms in cooperative multi-agent reinforcement learning are unclear.
method The paper introduces decomposable games and proves that applying the multi-agent fitted Q-Iteration algorithm leads to an optimal Q-function in these games.
result The paper offers theoretical insights into when and why value decomposition algorithms converge in cooperative multi-agent reinforcement learning.
New method stabilizes FQE by reweighting Bellman targets.
problem Stability guarantees for FQE often rely on Bellman completeness, which can fail with function approximation.
method Proposes stationary-weighted FQE, reweighting Bellman targets by stationary target-to-behavior density ratio.
result Proves finite-sample linear convergence to stationary projected Bellman fixed point without Bellman completeness.
The paper formalizes and analyzes multi-agent Q-learning with value factorization.
problem Understanding and improving the convergence of multi-agent Q-learning with value factorization.
method Formalized a multi-agent fitted Q-iteration framework for analyzing factorized multi-agent Q-learning.
result Multi-agent Q-learning with linear value factorization can converge under certain conditions.
New method solves tree-structured Schrödinger Bridge problems.
problem Computing Schrödinger Bridge between tree-structured distributions.
method Iterative Markovian Fitting (IMF) procedure for tree-structured costs.
result Extends IMF to tree-structured Schrödinger Bridge problems.
Value iteration is a fixed point iteration technique utilized to obtain the optimal value function and policy in a discounted reward Markov Decision Process (MDP). Here, a contraction operator is constructed and applied repeatedly to arrive at the optimal solution. Value iteration is a first order method and therefore …
When function approximation is deployed in reinforcement learning (RL), the same problem may be formulated in different ways, often by treating a pre-processing step as a part of the environment or as part of the agent. As a consequence, fundamental concepts in RL, such as (optimal) value functions, are not uniquely de…
A new method reduces the time needed for Bayesian optimization by a factor of 10-100.
problem Efficiently scaling Bayesian optimization to many observations.
method Epistemic Nearest Neighbors (ENN) for hyperparameter fitting and UCB acquisition.
result TuRBO-ENN reduces proposal time by one to two orders of magnitude compared to TuRBO.
Analyzes premium data of Indian non-life insurers, finding GEV distribution best fits Lognormal and GEV extremes.
problem Modeling premiums of non-life insurance companies in India.
method Empirical analysis using Lognormal, GEV, and GPD distributions.
result Generalized Extreme Value distribution best fits premium data for ten Indian non-life insurers.
Missing values, irregularly collected samples, and multi-resolution signals commonly occur in multivariate time series data, making predictive tasks difficult. These challenges are especially prevalent in the healthcare domain, where patients' vital signs and electronic records are collected at different frequencies an…
RWR converges to global optimum in certain settings.
problem Proving convergence of RWR to optimal policy.
method Iterative learning with return-weighted log-likelihood.
result RWR converges to global optimum under certain conditions.
Exact LAD line fitting via PALB with linear scaling and speed.
problem Robust line fitting for data with outliers.
method Piecewise Affine Lower-Bounding (PALB) method using supporting lines and subdivision scheme.
result Empirical log-linear scaling and significantly faster than LP and IRLS methods.
We give a simple and effective two stage algorithm for approximating a point cloud S⊂Rm by a simplicial complex K. The first stage is an iterative fitting procedure that generalizes k-means clustering, while the second stage involves deleting redundant simplices. A form of dimension reduct…
Given a linear regression setting, Iterative Least Trimmed Squares (ILTS) involves alternating between (a) selecting the subset of samples with lowest current loss, and (b) re-fitting the linear model only on that subset. Both steps are very fast and simple. In this paper we analyze ILTS in the setting of mixed linear …
New methods improve accuracy in detecting concentric objects.
problem Detecting concentric geometric objects in noisy data.
method Developed new estimators and compared performance of existing methods.
result New methods outperform existing non-iterative methods and are robust to noise.
Developed an efficient iterative algorithm for SVI model.
problem SVI model's optimizer's strong dependence on input starting point.
method Fixed-point and least-square optimizer.
result Convergence results for fixed-point iterative algorithm in certain situations.
We propose a data aggregation-based algorithm with monotonic convergence to a global optimum for a generalized version of the L1-norm error fitting model with an assumption of the fitting function. The proposed algorithm generalizes the recent algorithm in the literature, aggregate and iterative disaggregate (AID), whi…
Graph neural network executes value iteration for flexible environments.
problem Value iteration in flexible environments with direct supervision.
method Graph Neural Network (GNN) executing value iteration algorithm.
result GNN accurately models value iteration across diverse environments.
New algorithm learns value and advantage functions for continuous-time Markov processes without structural assumptions.
problem Learning value and advantage functions for continuous-time Markov processes without structural assumptions.
method Proposes Sobolev-prox fitted q-learning algorithm based on Hilbert-space positive definiteness and boundedness properties of Bellman operators. result Identifies ellipticity as a key structural property enabling reinforcement learning for Markov diffusions.
New findings show a balance between data fit and complexity in kernel hyperparameters.
problem Overcorrelation due to reparametrization of kernel hyperparameters.
method Reparametrization of kernel hyperparameters and analysis of marginal likelihood.
result Data fit term influences all other kernel hyperparameters, not just the complexity penalty.
SGD converges to optimal solution in perfect data fitting problem.
problem Noiseless least-squares with perfect data fitting.
method Last iterate of SGD with constant step-size.
result Convergence of SGD final iterate for non-strongly convex problem.
We present an off-policy actor-critic algorithm for Reinforcement Learning (RL) that combines ideas from gradient-free optimization via stochastic search with learned action-value function. The result is a simple procedure consisting of three steps: i) policy evaluation by estimating a parametric action-value function;…
The paper studies efficient Hessian fitting methods for stochastic optimization.
problem Efficient Hessian fitting for stochastic optimization.
method Preconditioned Stochastic Gradient Descent (PSGD) method and Lie groups.
result Hessian fitting problem is strongly convex in certain Lie groups.