New algorithms sample convex bodies using Markov chains and restricted Gaussian oracles.
problem Sampling uniformly from convex bodies efficiently.
method Markov chain Monte Carlo with proximal sampler and restricted Gaussian oracle.
result Efficient implementation of RGO for uniform sampling on convex bodies.
The method of block coordinate gradient descent (BCD) has been a powerful method for large-scale optimization. This paper considers the BCD method that successively updates a series of blocks selected according to a Markov chain. This kind of block selection is neither i.i.d. random nor cyclic. On the other hand, it is…
This paper studies the estimation of low-rank Markov chains from empirical trajectories. We propose a non-convex estimator based on rank-constrained likelihood maximization. Statistical upper bounds are provided for the Kullback-Leiber divergence and the ℓ2 risk between the estimator and the true transition matri…
Two strategies extend multi-label chaining for imprecise probability estimates.
problem Handling imprecise probability estimates in multi-label classification.
method Adapting multi-label chaining to use convex sets of distributions (credal sets).
result Adapted approaches produce relevant cautiousness on hard-to-predict instances.
Optimizes routing in decentralized exchanges with gas fees.
problem Routing in decentralized exchanges with fixed gas fees.
method General optimization framework with mixed-integer model, incorporating gas fees.
result Explicit Karush-Kuhn-Tucker system linking prices, fees, and activation.
We study a new notion of Ricci curvature that applies to Markov chains on discrete spaces. This notion relies on geodesic convexity of the entropy and is analogous to the one introduced by Lott, Sturm, and Villani for geodesic measure spaces. In order to apply to the discrete setting, the role of the Wasserstein metric…
Stochastic gradient methods are the workhorse (algorithms) of large-scale optimization problems in machine learning, signal processing, and other computational sciences and engineering. This paper studies Markov chain gradient descent, a variant of stochastic gradient descent where the random samples are taken on the t…
New method finds better arbitrage opportunities in AMMs.
problem Finding optimal arbitrage trades in multi-token AMMs.
method Closed-form solutions using convex optimisation.
result Better arbitrage opportunities than traditional methods.
Estimates covariance matrices using Markov chain Monte Carlo with improved sample complexity.
problem Complexity of covariance matrix estimation for Gibbs distributions.
method Uses Markov chain Monte Carlo with conditions on the chain's spectral gap and Poincaré inequality.
result Achieves similar sample complexity as i.i.d. samples with better query complexity.
LLMs predict SGD convergence without training on specific data.
problem Predicting SGD convergence without labeled data.
method Link between SGD and Markov chains, leveraging LLMs' understanding of dynamical systems.
result Zero-shot prediction of SGD convergence for new starting points.
SGD's uncertainty quantified in non-convex learning problems.
problem Uncertainty quantification in non-convex learning problems.
method Asymptotic normality of SGD iterates and bias characterization.
result SGD iterates are asymptotically normally distributed around the expected value of the invariant distribution.
Analyzes convex structures in Teichmüller space unit tangent spheres.
problem Characterize faces and extreme points of unit tangent spheres in Teichmüller space.
method Analyzes Finsler infinitesimal balls of Thurston metric, characterizes faces, exposed faces, and extreme points.
result Characterizes faces and extreme points of unit tangent spheres in Teichmüller space.
Existence proved for q-Bass martingales with specific marginals.
problem Constructing martingales with prescribed marginals close to a reference measure.
method Geometric analysis of parametrized convex polygonal chains.
result Existence and uniqueness of q-Bass martingales with finitely supported initial marginals. New method adapts to unknown mixing time in stochastic optimization.
problem Optimizing with Markovian data where mixing time is unknown.
method Combines MLMC gradient estimation with adaptive learning.
result Achieves optimal convergence rate for convex problems.
This thesis tackles non-convex Bayesian learning via scalable dynamic importance sampling algorithms.
problem Non-convex Bayesian learning problem in deep neural networks.
method Replica exchange Langevin Monte Carlo, control variates method, population-chain replica exchange, scalable dynamic importance sampling.
result Control variates method reduces variance and accelerates convergence in non-convex Bayesian learning.
We consider the problem of minimizing a convex objective function F when one can only evaluate its noisy approximation F^. Unless one assumes some structure on the noise, F^ may be an arbitrary nonconvex function, making the task of minimizing F intractable. To overcome this, prior work has often focu…
The paper analyzes SGD with Richardson-Romberg extrapolation for convex optimization problems.
problem Solving strongly convex and smooth minimization problems efficiently.
method Combining SGD with Polyak-Ruppert averaging and Richardson-Romberg extrapolation.
result An expansion of the mean-squared error of the estimator with respect to the number of iterations.
New algorithm robustly optimizes data streams with heavy-tailed or infinite variance samples.
problem Optimizing data streams with heavy-tailed or infinite variance samples.
method Gradient quantile clipping for SGD, leveraging Markov chain connections.
result Algorithm converges to a concentrated distribution with high probability bounds.
We address a portfolio selection problem that combines active (outperformance) and passive (tracking) objectives using techniques from convex analysis. We assume a general semimartingale market model where the assets' growth rate processes are driven by a latent factor. Using techniques from convex analysis we obtain a…
We systematically investigate the problem of representing Markov chains by families of random maps, and which regularity of these maps can be achieved depending on the properties of the probability measures. Our key idea is to use techniques from optimal transport to select optimal such maps. Optimal transport theory a…
Paper proves CLT for quantile SGD with constant learning rate.
problem Quantile estimation via SGD with non-smooth, non-strongly convex loss.
method Viewed as a Markov chain, derived stationary distribution, analyzed MGF, proved CLT.
result Centered and standardized stationary distribution converges to Gaussian as ηightarrow0. The paper provides privacy guarantees for MCMC algorithms using Langevin dynamics.
problem Ensuring differential privacy in MCMC algorithms.
method Novel methodology combining Girsanov's theorem and perturbation trick.
result Established (Rényi) DP guarantees for Langevin algorithms.
The paper studies the convex hull of random points in a triangle, focusing on the asymptotic behavior and phase transitions.
problem Analyzing the convex hull of random points in a triangle with a phase transition.
method Conditional analysis of the convex hull's boundary size and shape, proving phase transitions and convergence to specific curves.
result The convex hull's boundary converges to a hyperbola or parabola under specific conditions, solving an optimization problem.
New method fits sparse Markov models to categorical time series using convex clustering.
problem Exponentially growing parameters in higher-order Markov chains.
method Convex clustering and regularization for parsimonious modeling.
result Theoretical consistency and finite sample performance demonstrated.
New algorithm improves sampling from constrained spaces.
problem Sampling from constrained spaces efficiently.
method Metropolis-adjusted Mirror Langevin algorithm.
result Unbiased sampling with improved mixing time.
Robust algorithm for distributed optimization resistant to Byzantine failures.
problem Resilient optimization in the presence of unreliable agents.
method Temporal and spatial robust aggregation, gradient normalization.
result Convergence for strongly convex and non-convex functions.
The embedded contact homology (ECH) of a 3-manifold with a contact form is a variant of Eliashberg-Givental-Hofer's symplectic field theory, which counts certain embedded J-holomorphic curves in the symplectization. We show that the ECH of T^3 is computed by a combinatorial chain complex which is generated by labeled c…
Introduces HMC method for sampling Gibbs densities.
problem Sampling from Gibbs densities efficiently.
method Hamiltonian Monte Carlo (HMC) method based on Hamiltonian dynamics.
result Idealized HMC preserves the target distribution and converges under certain conditions.
New algorithms help machines forget old data efficiently.
problem Machine learning models can retain old data, hindering new learning.
method Developed TV-stable algorithms based on noisy SGD for convex and non-convex functions.
result Achieved efficient unlearning with upper and lower bounds on risk.
TML package uses tropical geometry for machine learning tasks.
problem Statistical learning problems.
method Tropical convexity computations, Hit and Run sampler, tropical metrics.
result First R package for tropical geometric machine learning.
When solving consensus optimization problems over a graph, there is often an explicit characterization of the convergence rate of Gradient Descent (GD) using the spectrum of the graph Laplacian. The same type of problems under the Alternating Direction Method of Multipliers (ADMM) are, however, poorly understood. For i…
Novel bounds improve TD learning consistency in RL.
problem Analyzing Temporal Difference learning's performance.
method High-dimensional concentration inequalities and Berry-Esseen bounds for Markov chain induced martingales.
result Sharp high-probability consistency guarantee for TD learning, matching asymptotic variance up to logarithmic factors.
Price of anarchy, the performance ratio, which could characterize the loss of efficiency of the distributed supply chain management compared with the integrated supply chain management is discussed by utilizing newsvendor problem in single period which is well-known. In particular, some of remarkable distributed polici…
Smooth curves from polygonal chains with vertex preservation and explicit curvature control.
problem Preserving vertices while smoothing polygonal chains to C∞ curves. method Directional mollification operator for polygonal chains.
result Smooth curves that intersect original vertices and maintain explicit curvature bounds.
New algorithm extends LMC to more complex potentials.
problem Addressing limitations of existing LMC methods.
method Inexact Proximal Langevin Algorithm (IPLA).
result Improved convergence rates and broader applicability.
Adversarial online nonparametric regression achieves optimal rates with locally adaptive learning.
problem Adversarial online nonparametric regression with general convex losses.
method Parameter-free learning algorithm leveraging chaining trees to compete against H{ö}lder functions, dynamically tracking and adapting to local smoothness variations.
result First computationally efficient algorithm with locally adaptive optimal rates for online regression in an adversarial setting.
This paper analyzes stability and generalization of Markov chain stochastic gradient methods.
problem Analyzing stability and generalization of Markov chain stochastic gradient methods.
method Algorithmic stability in statistical learning theory.
result Established optimal generalization bounds for both smooth and non-smooth cases.
Method measures weight similarity in neural networks using normalization and statistical inference.
problem Quantifying weight similarity in non-convex neural networks.
method Chain normalization rule and hypothesis-training-testing statistical inference.
result Weights of identical neural networks converge to similar local solutions.
We create consistent option surfaces without arbitrage.
problem Constructing consistent option surfaces free of arbitrage across different maturities.
method Combining PCA-Smolyak approximation with chain-consistent diffusion and c-EMOT bridge.
result Computable certificates for strong convexity, solver correctness, and Dupire/Greeks stability.
Proposes r2SGLD for efficient constrained exploration in non-convex learning.
problem Stagnation in high-temperature chains of reSGLD in distribution tails.
method r2SGLD: replica exchange with reflection steps in a bounded domain.
result Reflection steps enhance mixing rates with quadratic improvement in domain diameter.
This research improves neural likelihood approximation for Bayesian inverse problems.
problem Challenges in modeling and inference for high-dimensional Bayesian inverse problems.
method Develops a strictly convex approximation framework for neural likelihood.
result Empirical minimizers converge to the true likelihood as sample size increases.
An important task in machine learning and statistics is the approximation of a probability measure by an empirical measure supported on a discrete point set. Stein Points are a class of algorithms for this task, which proceed by sequentially minimising a Stein discrepancy between the empirical measure and the target an…
SGD converges to an invariant distribution with sub-Gaussian or sub-exponential properties.
problem Optimizing smooth and strongly convex objectives using SGD.
method Analysis through Markov chains, focusing on convergence and concentration properties.
result SGD iterates and their invariant limit distribution inherit sub-Gaussian or sub-exponential concentration properties.
Recent studies have illustrated that stochastic gradient Markov Chain Monte Carlo techniques have a strong potential in non-convex optimization, where local and global convergence guarantees can be shown under certain conditions. By building up on this recent theory, in this study, we develop an asynchronous-parallel s…
The paper analyzes convergence rates of Langevin dynamics and Proximal Sampler using Φ-divergence.
problem Analyzing convergence rates of Langevin dynamics and Proximal Sampler.
method Extending mixing time analyses to Φ-divergence, using strong data processing inequalities. result Convergence of Φ-divergence to 0 exponentially fast along Unadjusted Langevin Algorithm and Proximal Sampler. New rates for GLD and SGLD in infinite-dimensional spaces without dimensionality issues.
problem Gradient Langevin dynamics and SGLD convergence rates in high-dimensional spaces.
method Analysis of GLD and SGLD in infinite-dimensional Hilbert spaces, using stochastic differential equations and Markov chains.
result Derivation of dimension-free convergence rates for GLD and SGLD.
Stochastic Gradient Langevin Dynamics (SGLD) is a popular variant of Stochastic Gradient Descent, where properly scaled isotropic Gaussian noise is added to an unbiased estimate of the gradient at each iteration. This modest change allows SGLD to escape local minima and suffices to guarantee asymptotic convergence to g…
This paper develops a low-nonnegative-rank approximation method to identify the state aggregation structure of a finite-state Markov chain under an assumption that the state space can be mapped into a handful of meta-states. The number of meta-states is characterized by the nonnegative rank of the Markov transition mat…