uHMC achieves fast mixing in high dimensions with gradient evaluations.
problem Quantifying mixing time of uHMC in high dimensions.
method Construction of successful couplings for uHMC.
result uHMC mixes in total variation with logarithmic dependence on dimension.
Estimates Markov chain mixing time from a single trajectory.
problem Estimating mixing time of Markov chains from a single trajectory.
method Contraction with respect to total variation, inspired by Wolfer's contraction coefficient.
result Improved confidence intervals and instance-dependent rates for estimating Markov chains.
This work analyzes Gibbs samplers for Bayesian hierarchical models without dimensionality constraints.
problem Analyzing convergence properties of Gibbs samplers for Bayesian hierarchical models.
method Using Bayesian asymptotics and total variation mixing times, the study provides dimension-free convergence results.
result Dimension-free convergence results for Gibbs samplers targeting hierarchical models under random data-generating assumptions.
New RL theory reduces sample complexity for mixing MDPs.
problem Optimal sample complexity for reinforcement learning in mixing MDPs.
method Regeneration-type ideas to analyze mixing times.
result Optimal sample complexity depends on mixing time, not just discount factor.
We develop variation formulas for the quantities of extrinsic geometry for adapted variations of metrics on almost-product (e.g. foliated) Riemannian manifolds, and apply them to study the total mixed scalar curvature of a distribution -- analogue of the classical Einstein-Hilbert action. The mixed scalar curvature ${\…
We examine the total mixed scalar curvature of a fixed distribution as a functional of a pseudo-Riemannian metric. We develop variational formulas for quantities of extrinsic geometry of the distribution to find the critical points of this action. Together with the arbitrary variations of the metric, we consider also v…
Gibbs sampler mixes quickly for certain smooth distributions.
problem Drawing samples from log-smooth log-concave distributions.
method Analyzes Gibbs sampler on log-smooth and strongly log-concave distributions.
result Gibbs sampler mixes in O ⋆ ( κ 2 n 7.5 ) O^{\star}(κ^2 n^{7.5}) O ⋆ ( κ 2 n 7.5 ) steps. MALA mixes efficiently under smoothness and isoperimetry assumptions.
problem Sampling from target densities efficiently.
method Metropolis-Adjusted Langevin algorithm (MALA) with smoothness and isoperimetry assumptions.
result MALA mixes in $O\left(\frac{(LΥ)^{\frac12}}{ψ_μ^2} \log\left(\frac{1}ε
ight)
ight)$ iterations.
Sharp inequality between TV and Hellinger distances for Gaussian mixtures.
problem Understanding the relationship between total variation and Hellinger distances for Gaussian mixtures.
method Established a general upper bound on Hellinger distance in terms of TV distance raised to a power, demonstrating sharpness with specific examples.
result The Hellinger distance between two Gaussian mixtures is bounded by the TV distance raised to a power 1 − o ( 1 ) 1-o(1) 1 − o ( 1 ) , where o ( 1 ) o(1) o ( 1 ) is of order 1 / log log ( 1 / T V ) 1/\log\log(1/\mathrm{TV}) 1/ log log ( 1/ TV ) . Two algorithms learn Gaussian graphical models from Glauber dynamics trajectories.
problem Learning Gaussian graphical models from dependent data.
method Two complementary approaches: local edge-testing and burn-in/thinning reduction.
result Both approaches provide finite-sample recovery guarantees and empirical comparisons.
Study of Einstein-Hilbert action on metric-affine spaces with connections.
problem Formulating and solving variational problems for mixed Einstein-Hilbert action.
method Developed variational formulas for extrinsic geometry, derived Euler-Lagrange equations, and characterized critical points.
result Derived new equations analogous to Einstein and Cartan equations, with a new Ricci type tensor.
We develop variation formulas on almost-product (e.g. foliated) pseudo-Riemannian manifolds, and we consider variations of metric preserving orthogonality of the distributions. These formulae are applied to Einstein-Hilbert type actions: the total mixed scalar curvature and the total extrinsic scalar curvature of a dis…
New algorithm learns optimal policy for average reward MDPs with sample complexity matching lower bound.
problem Learning optimal policy for average reward in uniformly ergodic MDPs.
method Developed an estimator with sample complexity of O(|S||A|t_{mix}ε^{-2}).
result First algorithm to match lower bound of existing literature.
New method improves uncertainty estimation in complex statistical models.
problem Challenges in estimating high-dimensional mixed models due to computational complexity.
method Partially factorized variational inference to relax mean-field assumption.
result Relaxed variational inference provides accurate uncertainty quantification without high computational cost.
Closed Riemannian manifolds with positive mixed sectional curvature
problem Constructing closed Riemannian manifolds with positive mixed sectional curvature
method Explicit construction using totally geodesic foliations
result Positive mixed sectional curvature alone does not imply the Ferus--Adams estimate on closed manifolds
We consider a problem of prescribing the partial Ricci curvature on a locally conformally flat manifold ( M n , g ) (M^n, g) ( M n , g ) endowed with the complementary orthogonal distributions D 1 D_1 D 1 and D 2 D_2 D 2 . We provide conditions for symmetric ( 0 , 2 ) (0,2) ( 0 , 2 ) -tensors T T T of a simple form (defined on M M M ) to admit metrics g ~ \tilde g g ~ , conformal to …
Improved Metropolized HMC runtime for logconcave distributions.
problem Improving the runtime of Metropolized HMC for logconcave sampling.
method Gradient norm concentration and new mixing time analysis techniques.
result Metropolized HMC mixes in O ~ ( κ d ) \tilde{O}(κd) O ~ ( κ d ) iterations, improving runtime by a factor of ( κ / d ) 1 / 2 (κ/d)^{1/2} ( κ / d ) 1/2 . Paper proposes a mean-field gradient descent for zero-sum games, proving convergence to Nash equilibrium.
problem Finding mixed Nash equilibria in zero-sum games with multiple players.
method Mean-field gradient descent dynamics with time-averaging, incorporating exponentially discounted gradients.
result Exponential convergence rate to mixed Nash equilibrium with respect to total variation metric.
Lower bound on BART's mixing time increases with data points.
problem Slow mixing time in BART's MCMC chains.
method Simplified BART with a single tree and reduced MCMC moves.
result Mixing time grows exponentially with data points.
New method optimizes non-linear functionals over probability measures.
problem Optimizing non-linear functionals defined over probability measures.
method N-particle underdamped Langevin algorithm with spacetime discretization.
result Converges globally in total variation distance.
New method trains Markov kernels for efficient sampling.
problem Efficient sampling from complex probability distributions.
method Adversarial learning of involutive Metropolis-Hastings kernels.
result Minimizes total variation distance to empirical data.
The paper studies curves in Riemannian manifolds using total variation flow.
problem Analyzing the evolution of curves in Riemannian manifolds using total variation.
method Defining and proving the existence of strong solutions to the flow equations, showing variational equality, and proving convergence.
result Strong solutions converge to a constant map in finite time for non-positive sectional curvature.
Estimates missing mass in Markovian sequences with linear runtime and near-optimal risk.
problem Estimating missing mass in Markovian sequences.
method Windowed Good-Turing (WingIt) estimator.
result Risk decays as O ~ ( T m i x / n ) \widetilde{O}(\mathsf{T_{mix}}/n) O ( T mix / n ) , independent of state space size. Introduces HTV to measure function complexity in learning schemes.
problem Assessing the complexity of supervised-learning schemes.
method Defines Hessian-Schatten total variation (HTV) as a seminorm to quantify function complexity.
result HTV is invariant to rotations, scalings, and translations, and its minimum value is achieved for linear mappings.
A scalable model for high-dimensional longitudinal data.
problem Modeling high-dimensional, non-linear, time-varying longitudinal data.
method LMM-VAE, combining linear mixed models and amortized variational inference.
result Competitive performance across simulated and real-world datasets.
Estimates stationary mass and frequency from non-i.i.d. data.
problem Estimating stationary mass and frequency from non-i.i.d. data.
method Combines plug-in estimator with WingIt modification for exponentially α α α -mixing processes. result Universal consistency in n n n for total variation distance estimation. We give a way of constructing real variations of mixed Hodge structures over compact Kähler manifolds by using mixed Hodge structures on Sullivan's 1 1 1 -minimal models of certain differential graded algebras associated with real variations of Hodge structures.
RHMC accelerates sampling from log-concave distributions.
problem Sampling from log-concave probability distributions efficiently.
method RHMC uses simulated Hamiltonian dynamics with random integration times.
result RHMC converges exponentially fast in KL divergence for log-concave distributions.
Improved state estimation in nonlinear models using amortized backward variational inference.
problem State estimation in general state-space models.
method Amortized backward variational inference with neural network parameters.
result Linear growth of variational approximation error in number of observations.
New algorithms sample structured logconcave families with improved efficiency.
problem Sampling structured logconcave families to high accuracy.
method Reduction framework inspired by proximal point methods, combined with restricted Gaussian oracles.
result Improved bounds for sampling structured distributions, matching or surpassing state-of-the-art results.
HMC with leapfrog integrator mixes faster than MALA under certain smoothness conditions.
problem Analyzing the mixing time of HMC and MALA for sampling from smooth distributions.
method Bounding gradient complexity and leveraging invariance of joint distribution.
result Metropolized HMC with more leapfrog steps outperforms MALA in total variation distance.
Many real-valued stochastic time-series are locally linear (Gassian), but globally non-linear. For example, the trajectory of a human hand gesture can be viewed as a linear dynamic system driven by a nonlinear dynamic system that represents muscle actions. We present a mixed-state dynamic graphical model in which a hid…
We present an affine-invariant random walk for drawing uniform random samples from a convex body K ⊂ R n \mathcal{K} \subset \mathbb{R}^n K ⊂ R n that uses maximum volume inscribed ellipsoids, known as John's ellipsoids, for the proposal distribution. Our algorithm makes steps using uniform sampling from the John's ellipsoid of the …
Efficiently estimates binary product distributions with privacy.
problem Estimating means of binary product distributions privately and accurately.
method Polynomial time, pure differential privacy approach.
result Optimal sample complexity with polylogarithmic factors.
Paper introduces a new method to model epidemic dynamics with varying parameters.
problem Capturing discontinuous variations in epidemic model parameters.
method Total variation regularization with Iterated Nelder--Mead optimization.
result The method accurately models epidemic dynamics with instant changes.
MMM model clusters mixed-type longitudinal data efficiently.
problem Challenges in clustering multivariate longitudinal mixed-type data.
method MMM model reorganizes data into a three-way structure, using a mixture of matrix-variate normal distributions.
result MMM model handles various data types (continuous, ordinal, binary, nominal, count) and temporal dependence.
Robustly clusters mixtures of Gaussians even with outliers.
problem Clustering mixtures of statistically separated Gaussians robustly to outliers.
method Uses certifiable hypercontractivity, bounded variance, and anti-concentration of linear projections.
result First efficient algorithm for robust clustering of statistically separated Gaussians mixtures.
Based on a study of the coupling by reflection of diffusion processes, a new monotonicity in time of a time-dependent transportation cost between heat distribution is shown under Bakry-Emery's curvature-dimension condition on a Riemannian manifold. The cost function comes from the total variation between heat distribut…
Unified framework for solving MDPs with stochastic mirror descent.
problem Approximately solving infinite-horizon Markov decision processes (MDPs).
method Primal-dual stochastic mirror descent for MDPs with a unified framework.
result Computes ε-optimal policies with expected samples for both average-reward and discounted MDPs.
Paper proposes new density estimators for high-dimensional data.
problem Prohibitive computational cost and slow convergence rate in high-dimensional density estimation.
method Adaptive hyperbolic cross density estimators in mixed smooth Sobolev spaces.
result Proposed estimators do not suffer curse of dimensionality under Integral Probability Metrics.
Study shows linear sample complexity for learning SPNs.
problem Learning the set of distributions represented by Sum-Product Networks (SPNs).
method Initiate study of sample complexity, show linear growth up to logarithmic factors, use distribution compression schemes.
result Sample complexity grows linearly with the number of parameters of the SPN.
Develops a new method for learning discrete distributions without embedding them in a continuous space.
problem Challenges in learning discrete distributions using current methodologies.
method Introduces a MAD invertible map and a mixed variational flow (MAD Mix) for discrete distributions.
result MAD Mix produces more reliable approximations than continuous-embedding flows.
Study variational problem on manifold with special distributions.
problem Generalize Einstein metrics on manifold with multiple distributions.
method Define functional of pseudo-Riemannian metric and contorsion tensor, prove critical pairs make distributions totally umbilical.
result Metrics in critical pairs make all distributions totally umbilical.
Study on surfaces in product space with curvature inequality.
problem Characterizing surfaces in S n i m e s R \mathbb{S}^n imes \mathbb{R} S n im es R with total mean curvature. method Defined differential operators and proved integral inequalities.
result Integral inequality for closed stationary H \mathcal{H} H -surfaces in S n i m e s R \mathbb{S}^n imes \mathbb{R} S n im es R . VNA solves large portfolio optimization problems efficiently.
problem Large-scale portfolio optimization under real-world constraints.
method Mapped to Ising-like Hamiltonian and solved with VNA.
result Identifies near-optimal solutions for over 2,000 assets.
Sample measures of top centile contributions to the total (concentration) are downward biased, unstable estimators, extremely sensitive to sample size and concave in accounting for large deviations. It makes them particularly unfit in domains with power law tails, especially for low values of the exponent. These estima…
Machine learning models accurately predict the state and dynamics of reactive mixing.
problem Accurate prediction of reactive mixing for Earth and environmental science applications.
method Built a high-fidelity numerical model to simulate reactive mixing scenarios. Used 20 different machine learning emulators to classify mixing state and predict three QoIs.
result Ensemble methods and MLP models accurately predict the state of reactive mixing and QoIs, significantly faster than high-fidelity simulations.
Algorithm learns affine transformations robustly from corrupted samples.
problem Learning affine transformations from corrupted samples.
method New geometric certificate and iterative improvement method.
result Total variation distance of O ( ε ) O(ε) O ( ε ) between learned and original distributions.