Strong stability of ergodic iterations proven without ergodic driving sequence.
problem Ensuring strong stability of ergodic iterations under non-ergodic driving sequences.
method Revisiting processes driven by stationary ergodic sequences, proving strong stability under mild conditions on recursive maps.
result Strong stability of iterations proven without ergodic driving sequence.
Paper proves convergence of Markovian iteration for FBSDEs with fully coupled drift and Z process.
problem Proving convergence of Markovian iteration for FBSDEs with fully coupled drift and Z process.
method Differentiation-based approach to handle Z process, uniformly controlling Lipschitz continuity of decoupling fields.
result Proves convergence of Markovian iteration method for FBSDEs with fully coupled drift and Z process.
This dissertation advances scalable Gaussian processes using iterative methods and pathwise conditioning.
problem The classical Gaussian process formulation is not scalable for large datasets and modern hardware.
method Combining iterative methods and pathwise conditioning to improve scalability.
result Significantly reduced memory requirements and facilitated application to larger datasets.
New recommendations improve Gaussian process accuracy and stability.
problem Numerical instabilities and poor test likelihoods in iterative Gaussian process learning.
method Investigated CG tolerance, preconditioner rank, and Lanczos decomposition rank. Recommended small CG tolerance and large root decomposition size.
result L-BFGS-B optimizer achieves convergence with fewer gradient updates, improving Gaussian process accuracy.
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). IDBM solves Schrödinger bridge problems with iterative sampling.
problem Optimizing transport between probability measures.
method Iterated diffusion bridge mixture (IDBM) procedure.
result IDBM realizes valid transport between target measures at each iteration.
This paper speeds up iterative GP inference with warm starting.
problem Improving scalability of Gaussian process inference.
method Warm starting sequential posteriors using known solutions.
result Significant speed-ups and improved Bayesian optimisation performance.
Warm starts improve Gaussian process regression by up to 16x.
problem Optimizing hyperparameters for Gaussian processes.
method Iterative Gaussian processes with warm start optimization.
result Warm starts achieve the same results as conventional methods but significantly speed up computations.
This work uses QPGPs to improve ILC performance in repetitive tasks.
problem Performance degradation in repetitive motion tasks due to environmental changes and robot wear.
method Incorporates Quasi-Periodic Gaussian Processes into a predictive ILC framework.
result The proposed approach achieves faster convergence and robustness under disturbances.
New iterative methods improve scalability of Gaussian process approximations for large data.
problem Scalability issues in Gaussian process approximations for large spatial data.
method Iterative methods combined with preconditioners to reduce computational costs.
result Preconditioners accelerate convergence and improve predictive variances.
Improved image generation through iterative flow matching to reduce hallucinations.
problem Hallucinations in image generation models.
method Iterative flow matching to refine and correct paths in generative models.
result Enhanced generative modeling with reduced unrealistic images.
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 …
Novel algorithm for Markov decision processes using rank-one approximation.
problem Solving planning and learning problems of Markov decision processes.
method Policy iteration with rank-one approximation of transition probability matrix.
result The proposed algorithm consistently outperforms first-order algorithms and their accelerated versions.
Improved generalization with iterate averaging and adaptive algorithms.
problem Enhancing model generalization performance in high-dimensional settings.
method Gaussian process perturbation model, combine IA with large learning rates and regularisation, less frequent averaging, adaptive gradient methods.
result Iterate averaging with adaptive algorithms significantly outperforms SGD on various datasets.
We propose a novel method for maximum likelihood-based parameter inference in nonlinear and/or non-Gaussian state space models. The method is an iterative procedure with three steps. At each iteration a particle filter is used to estimate the value of the log-likelihood function at the current parameter iterate. Using …
Recurrent iterated function systems (RIFSs) are improvements of iterated function systems (IFSs) using elements of the theory of Marcovian stochastic processes which can produce more natural looking images. We construct new RIFSs consisting substantially of a vertical contraction factor function and nonlinear transform…
We propose a novel adversarial learning strategy for mixture models of Hawkes processes, leveraging data augmentation techniques of Hawkes process in the framework of self-paced learning. Instead of learning a mixture model directly from a set of event sequences drawn from different Hawkes processes, the proposed metho…
Data application developers and data scientists spend an inordinate amount of time iterating on machine learning (ML) workflows -- by modifying the data pre-processing, model training, and post-processing steps -- via trial-and-error to achieve the desired model performance. Existing work on accelerating machine learni…
The paper analyzes when credal sets stabilize under iterative updates in machine learning.
problem When do credal sets stabilize under iterative updates in machine learning?
method Fixed-point theorems for credal set updates.
result The paper provides the first analysis of credal set stability.
Efficiently differentiate functions of large matrices using new adjoint systems.
problem Differentiating functions of large matrices in scientific and probabilistic machine learning models.
method Deriving and implementing new adjoint systems for Lanczos and Arnoldi iterations in JAX.
result Efficient differentiation of PDEs, Gaussian process models, and Bayesian neural networks.
New method speeds up Gaussian process training and inference for large datasets.
problem Training and inference in Gaussian processes are computationally expensive for large datasets.
method Iterative alternating projection method that accesses subblocks of the kernel matrix, reducing time and space complexity.
result Empirically, the method accelerates GP training and inference by up to 72x compared to conjugate gradients.
New algorithms solve robust MDPs efficiently, significantly faster than existing methods.
problem Computing robust MDP solutions with uncertainty in transition probabilities is computationally expensive.
method Partial policy iteration and fast robust Bellman operator computation methods.
result The proposed methods are many orders of magnitude faster than state-of-the-art approaches.
Signal retrieval from a series of indirect measurements is a common task in many imaging, metrology and characterization platforms in science and engineering. Because most of the indirect measurement processes are well-described by physical models, signal retrieval can be solved with an iterative optimization that enfo…
Paper constructs hyperbolic Coxeter groups that virtually fiber over Z.
problem Creating hyperbolic Coxeter groups that virtually fiber.
method Iterative procedure combining Jankiewicz-Norin-Wise results and Osajda's construction.
result Proves construction of groups with increasing vcd with each iteration.
Develops new samplers to approximate target distributions via modified Markov processes.
problem Approximating a target distribution with a modified Markov process.
method Iterative proportional fitting and Sinkhorn algorithm to modify transition kernels.
result Schrödinger bridge samplers can approximate target distributions and estimate their normalizing constants.
This paper approximates SA iterates using Gaussian distributions for tail bounds.
problem Characterizing the distribution of stochastic approximation iterates in finite time.
method Approximating pre-limit distributions of SA iterates by Gaussian sequences with recursively defined covariances.
result Explicit bounds on the Wasserstein-1 distance between rescaled iterates and Gaussians.
Recently, deep neural networks (DNNs) have shown advantages in accelerating optimization algorithms. One approach is to unfold finite number of iterations of conventional optimization algorithms and to learn parameters in the algorithms. However, these are forward methods and are indeed neither iterative nor convergent…
Proposes a new method for GNNs that avoids iterative node state convergence.
problem Iterative computation of node states in GNNs is inefficient and requires many epochs.
method Constrained optimization in the Lagrangian framework to learn transition function and node states simultaneously.
result The proposed method compares favorably with existing models on various benchmarks.
Study optimality in safety-constrained Markov decision processes using asynchronous value iteration and modified Q-learning.
problem Optimality in safety-constrained Markov decision processes with multichain structure.
method Formulated as a zero-sum game, constructed asynchronous value iteration scheme and modified Q-learning algorithm.
result Resolved Bellman's principle of optimality for multichain Markov decision processes and provided learning algorithms.
The paper speeds up hyperparameter optimisation in Gaussian processes.
problem Scaling hyperparameter optimisation to large datasets.
method Improvements to linear system solvers (pathwise gradient, warm starting, early stopping).
result Speed-ups of up to 72x and residual norm decreases of up to 7x.
Alternating direction method of multiplier (ADMM) is a popular method used to design distributed versions of a machine learning algorithm, whereby local computations are performed on local data with the output exchanged among neighbors in an iterative fashion. During this iterative process the leakage of data privacy a…
A new approach for feature extraction from time series is proposed in this paper. This approach consists of a specific regression model incorporating a discrete hidden logistic process. The model parameters are estimated by the maximum likelihood method performed by a dedicated Expectation Maximization (EM) algorithm. …
Paper proposes a new method to solve Schrödinger Bridge Problem using kernel regression.
problem Schrödinger Bridge Problem in the context of entropic optimal transport.
method Forward-reverse iterative Monte Carlo procedure using kernel regression.
result Developed a provably convergent algorithm for approximating Schrödinger potentials.
In this paper, we propose a novel policy iteration method, called dynamic policy programming (DPP), to estimate the optimal policy in the infinite-horizon Markov decision processes. We prove the finite-iteration and asymptotic l\infty-norm performance-loss bounds for DPP in the presence of approximation/estimation erro…
IBPF algorithm tackles high-dimensional parameter learning for complex systems.
problem Learning high-dimensional parameters in complex, partially observed, and nonlinear systems.
method Iterated Block Particle Filter (IBPF) for graphical state space models.
result IBPF algorithm consistently beats the curse of dimensionality across various experiments.
Warm-start strategies speed up GP inference by 19x.
problem Efficient sequential inference in Gaussian processes.
method Three warm-start strategies exploiting smaller linear systems.
result Warm-starting achieves up to 19x speed-up in convergence.
Many recent successful (deep) reinforcement learning algorithms make use of regularization, generally based on entropy or Kullback-Leibler divergence. We propose a general theory of regularized Markov Decision Processes that generalizes these approaches in two directions: we consider a larger class of regularizers, and…
An important result from psycholinguistics (Griffiths & Kalish, 2005) states that no language can be learned iteratively by rational agents in a self-sustaining manner. We show how to modify the learning process slightly in order to achieve self-sustainability. Our work is in two parts. First, we characterize iterated …
Unified bounds for iterative algorithms with Gaussian data matrices.
problem Establishing non-asymptotic bounds for iterative algorithms with Gaussian data.
method Explicit coupling between iterates and Gaussian process with deterministic covariance.
result Tight, dimension-free bounds for generalized first-order methods.
This work's purpose is to understand the dynamics of limit order books in order-driven markets. We try to illustrate a dynamical trading mechanism attached to the microstructure of limit order markets. We capture the iterative nature of trading processes, which is critical in the dynamics of bid-ask pairs and the switc…
This paper presents a way of solving Markov Decision Processes that combines state abstraction and temporal abstraction. Specifically, we combine state aggregation with the options framework and demonstrate that they work well together and indeed it is only after one combines the two that the full benefit of each is re…
Scalable Gaussian processes with latent Kronecker structure for large datasets.
problem Limited scalability of Gaussian processes for large datasets.
method Leveraging latent Kronecker structure, projecting kernel matrix onto latent Kronecker product, using iterative linear system solvers and pathwise conditioning.
result Outperforms state-of-the-art sparse and variational GPs on real-world datasets with up to five million examples.
IRKSN algorithm achieves sparse recovery with wider applicability conditions.
problem Sparse recovery challenges due to NP-hard nature and restrictive conditions.
method IRKSN algorithm based on k-support norm regularizer. result Achieves sparse recovery with explicit constants and standard linear rate.
New method explains GNNs using power iteration clustering.
problem Mysterious mechanism of message passing in GNNs.
method Subspace power iteration clustering (SPIC) models.
result Message passing in GNNs can be understood through power iteration.
A new robust GP regression algorithm that trims outliers improves model accuracy.
problem Severe bias in GP regression due to data contamination by outliers.
method Iterative trimming of extreme data points.
result Significantly outperforms standard and robust GP variants in most test cases.
The performance of deep (reinforcement) learning systems crucially depends on the choice of hyperparameters. Their tuning is notoriously expensive, typically requiring an iterative training process to run for numerous steps to convergence. Traditional tuning algorithms only consider the final performance of hyperparame…
Privacy amplification improved through contraction coefficients and Eγ-divergence.
problem Improving privacy guarantees in iterative algorithms.
method Using contraction coefficients derived from Eγ-divergence to determine differential privacy parameters. result Tighter bounds on differential privacy parameters of iterative algorithms.
New study shows faster convergence of SGD and Kaczmarz methods.
problem Improving convergence rates of iterative linear system solvers.
method Last-iterate convergence analysis of SGD with greedy step size over smooth quadratics.
result The t-th iterate attains an O(1/t3/4) convergence rate.