Proves subgaussian distributions are SoS-certifiably subgaussian, enabling efficient algorithms for various statistical tasks.
problem Efficiently learning from subgaussian distributions in high dimensions.
method Universal constant C and polynomial sum of squares (SoS) approach. result Proves subgaussian distributions are SoS-certifiably subgaussian.
Paper proves generalized Talagrand inequality for Sinkhorn distance.
problem Proving a generalized Talagrand inequality for Sinkhorn distance.
method Using entropy power inequality and infinitesimal displacement convexity of optimal transport map.
result Extends previous results of Gaussian Talagrand inequality for Sinkhorn distance to strongly log-concave case.
Paper refines Talagrand inequality on Euclidean spaces.
problem Improving Talagrand inequality for Euclidean spaces.
method Symmetrization and alternative proof methods.
result Several refined functional inequalities derived.
Paper introduces information-constrained optimal transport, generalizing Talagrand's inequality.
problem Optimal transport problem with information constraints.
method Information constrained variation of optimal transport, using Marton's approach.
result Recovery of concentration of measure results and solution to Cover's open problem.
Unified framework for information-theoretic bounds on learning algorithms.
problem Deriving generalization bounds for learning algorithms.
method Probabilistic decorrelation lemma, symmetrization, couplings, chaining, Young's inequality.
result New upper bounds on generalization error in expectation and high probability.
Estimates matrix trace optimization with statistical learning theory.
problem Optimizing trace of parameter-dependent matrices.
method Monte Carlo estimator with bounds derived from epsilon nets and generic chaining.
result Predicts small sampling amount for matrices with small off-diagonal mass.
This research analyzes the error convergence rate of GAN models.
problem Understanding the error convergence rate of GAN models.
method Applying Talagrand inequality and Borel-Cantelli lemma to establish a tight convergence rate.
result Established a tight convergence rate for the error of GAN models.
The paper provides a new uniform tail bound for empirical processes.
problem Developing a uniform tail bound for empirical processes indexed by a class of functions.
method Introducing a deflation step to the standard generic chaining argument, and using a natural seminorm based on Cramér functions.
result Established a new uniform tail bound for empirical processes.
Proves error bounds for PGD, extending log-Sobolev and Talagrand inequalities.
problem Maximum likelihood estimation of large latent variable models.
method Extending log-Sobolev and Talagrand inequalities to models with strongly concave log-likelihoods.
result Non-asymptotic error bounds for PGD in models satisfying LSI and PŁI.
New findings show Rademacher complexities are not crucial for learning complexities.
problem Understanding the sample complexity of learning with squared loss in convex classes.
method Novel learning procedure combining mean estimation and Talagrand's generic chaining method.
result Sample complexity is determined by the limiting Gaussian process, not Rademacher complexities.
We define a Hamilton-Jacobi semigroup acting on continuous functions on a compact length space. Following a strategy of Bobkov, Gentil and Ledoux, we use some basic properties of the semigroup to study geometric inequalities related to concentration of measure. Our main results are that (1) a Talagrand inequality on a …
Study generalizes matrix completion with side info in low noise settings.
problem Matrix completion with side information in low noise conditions.
method Inductive matrix completion with i.i.d. subgaussian noise, uniform sampling, and side information.
result Generalization bounds with noise scaling, convergence to zero, and logarithmic dependence on matrix size.
New bounds link generalization to stochastic optimizer's lower tail exponents.
problem Understanding the impact of stochastic optimization algorithms on generalization in non-convex settings.
method Proves novel bounds linking generalization to the lower tail exponent of the transition kernel of stochastic optimizers, both discrete- and continuous-time.
result Empirical results show correlations between generalization error and lower tail exponents.
Paper improves risk bound for MTL with graph-dependent data.
problem Sub-optimal risk bound in multi-task learning with graph-dependent data.
method Proposes a new Bennett-type inequality and develops new Talagrand-type inequality and local fractional Rademacher complexity.
result Derives a sharper risk bound of O(nlogn). We investigate the m-relative entropy, which stems from the Bregman divergence, on weighted Riemannian and Finsler manifolds. We prove that the displacement K-convexity of the m-relative entropy is equivalent to the combination of the nonnegativity of the weighted Ricci curvature and the K-convexity of the weig…
We introduce a class of generalized relative entropies (inspired by the Bregman divergence in information theory) on the Wasserstein space over a weighted Riemannian or Finsler manifold. We prove that the convexity of all the entropies in this class is equivalent to the combination of the nonnegative weighted Ricci cur…
Improved generalization bounds for CNNs using Rademacher complexity.
problem Establishing non-vacuous generalization bounds for deep learning models.
method Rademacher complexity framework with novel contraction lemmas for high-dimensional mappings.
result Enhanced generalization bounds for a broader class of activation functions.
We derive weighted log-Sobolev inequalities from a class of super Poincaré inequalities. As an application, the Talagrand inequality with larger distances are obtained. In particular, on a complete connected Riemannian manifold, we prove that the $\log^\dd$-Sobolev inequality with $\dd\in (1,2)$ implies the $L^{2/(2-\d…
Paper reinterprets majorizing measure theorem in terms of coding theory.
problem Understanding boundedness of random processes.
method Information-theoretic perspective using variable-length codes.
result Boundedness of random processes linked to efficient coding.
Study non-asymptotic bounds on correlation in high-dimensional linear systems, revealing invariant subspaces and bottlenecks.
problem Understanding correlation and mixing in high-dimensional linear systems with Gaussian noise.
method Sampling from sub-trajectories, using Talagrand's inequality, and analyzing invariant subspaces.
result Large discrepancy between algebraic and geometric multiplicity leads to bottlenecks between invariant subspaces.
Study non-Gaussian measures' concentration properties in metric spaces.
problem Concentration properties for non-linear Gaussian functionals with non-Gaussian tails.
method Prove generalised Transportation-Cost Inequalities (TCIs) for specific functionals.
result Extended TCIs for rough volatility and Parabolic Anderson Model.
This manuscript presents some new impossibility results on adversarial robustness in machine learning, a very important yet largely open problem. We show that if conditioned on a class label the data distribution satisfies the W2 Talagrand transportation-cost inequality (for example, this condition is satisfied if t…
Generic groups satisfy a chain condition for subgroups.
problem Understanding subgroup structures in generic groups.
method Proving for fixed integers m,t,k in generic m-generator t-relator groups. result Generic groups satisfy the Ascending Chain Condition for k-generated subgroups. A note proves the binary perceptron's capacity is less than 0.847.
problem Determining the capacity of the binary perceptron.
method Conditional first moment method combined with known results on the spherical perceptron.
result Proves the binary perceptron's capacity is less than 0.847.
Kernel-based L2-boosting with structure constraints improves regression efficiency.
problem Developing efficient kernel methods for regression.
method Kernel-based re-scaled boosting with truncation (KReBooT).
result KReBooT achieves near overfitting resistance and sparse estimates.
A new method simulates a lazy version of a Markov chain for empirical inference.
problem Estimating and testing unknown Markov chains with limited data.
method Simulates an α-lazy version of an unknown Markov chain, making it ergodic.
result The pseudo spectral gap can be applied to non-ergodic Markov chains.
A method for learning with autoregressive chain-of-thoughts.
problem Learning prompt-to-answer mappings from sequence-to-next-token generators.
method Iterating a fixed, time-invariant generator for multiple steps to generate a chain-of-thought, then taking the final token as the answer.
result Universal representability and computationally tractable chain-of-thought learning for a simple base class.
Study finds on-chain data can proxy off-chain cryptocurrency pricing.
problem Develop methods to proxy off-chain cryptocurrency pricing using on-chain data.
method Graphical models, mutual information, and ensemble machine learning.
result A significant amount of pricing information is contained in on-chain data, but precise prices are hard to recover except on short time scales.
The paper extends Hoeffding's inequality for Markov chains using a generalized concentrability condition.
problem Applying Hoeffding's inequality to non-ergodic Markov chains.
method Integrates generalized concentrability condition via IPM to extend traditional hypotheses.
result Demonstrates utility in machine learning applications such as empirical risk minimization and bandits.
In this paper, we introduce the notion of Reidemeister torsion for quasi-isomorphisms of based chain complexes over a field. We call a chain map a quasi-isomorphism if its induced homomorphism between homology is an isomorphism. Our notion of torsion generalizes the torsion of acyclic based chain complexes, and is a ch…
Study on identifying AMP chain graph models under known and unknown component decompositions.
problem Identifying AMP chain graph models with known and unknown chain component decompositions.
method Analyzes conditions for identifiability of AMP models and proposes algorithms for structure recovery.
result Conditions for DAG identifiability in AMP models extend equal variance criteria for Bayes nets.
Improves multi-label classification with a new network model.
problem Improving multi-label classification accuracy.
method Introduces Classifier Chain Network (CCN) for multi-label classification.
result CCN outperforms benchmark methods in simulations and real data.
Hidden Markov Chains and Linear-chain CRFs are equivalent.
problem Comparing Hidden Markov Chains and Conditional Random Fields.
method Constructing an HMC with the same posterior distribution as a CRF.
result HMCs and linear-chain CRFs are equivalent models.
DCDC calculates convergence rates for Markov chains using neural networks.
problem Computing precise convergence rates for Markov chains is hard.
method Developed a neural network-based algorithm (DCDC) to bound convergence rates in Wasserstein distance.
result Demonstrated effective convergence bounds for real-world Markov chains.
Generative neural samplers estimate quantum spin system properties.
problem Estimating observables for quantum spin systems.
method Autoregressive models using Suzuki-Trotter transformation.
result Results for energy, specific heat, and susceptibility are in good agreement with Monte Carlo methods.
We prove a new generalization bound that shows for any class of linear predictors in Gaussian space, the Rademacher complexity of the class and the training error under any continuous loss ℓ can control the test error under all Moreau envelopes of the loss ℓ. We use our finite-sample bound to directly recover…
The aim of this paper is to define a chain level refinement of the Batalin-Vilkovisky (BV) algebra structure on the homology of the free loop space of a closed, oriented C∞-manifold. For this purpose, we define a (nonsymmetric) cyclic dg operad which consists of "de Rham chains" of free loops with marked points…
We introduce and study the notion of a chain group of homeomorphisms of a one-manifold, which is a certain generalization of Thompson's group F. The resulting class of groups exhibits a combination of uniformity and diversity. On the one hand, a chain group either has a simple commutator subgroup or the action of the…
We present a new family of models that is based on graphs that may have undirected, directed and bidirected edges. We name these new models marginal AMP (MAMP) chain graphs because each of them is Markov equivalent to some AMP chain graph under marginalization of some of its nodes. However, MAMP chain graphs do not onl…
The paper tackles learning from non-irreducible Markov chains, proving learnability and generalization bounds.
problem Learning from temporal dependent data with non-irreducible Markov chains.
method Uniform convergence and generalization bounds for sample error under uniform ergodicity.
result Learnability and generalization bounds for approximate sample error minimization algorithm.
In his 2011 work, Maas has shown that the law of any time-reversible continuous-time Markov chain with finite state space evolves like a gradient flow of the relative entropy with respect to its stationary distribution. In this work we show the converse to the above by showing that if the relative law of a Markov chain…
Study Markov chain gradient descent in Hilbert spaces for quadratic loss.
problem Approximating optimal solutions for quadratic loss functions.
method Developed a Markov chain-based stochastic gradient algorithm in Hilbert spaces.
result Established probabilistic upper bounds on convergence.
We analyze a new Markov chain model for better sampling and optimization.
problem Developing a new Markov chain model for improved sampling and optimization.
method We introduce a new class of Ito chains with arbitrary noise and inexact drift/diffusion coefficients, proving a bound in W2-distance. result Our analysis provides improved or first results for various applications like SGLD, sampling, and boosting.
Paper proposes semi-supervised learning with triplet Markov chains.
problem Lack of labels in training data.
method Variational Bayesian inference for semi-supervised learning.
result Derives semi-supervised algorithms for various sequential models.
This work improves generalisation bounds using chaining and information theory.
problem Improving generalisation bounds for supervised learning algorithms.
method Developed a theoretical framework linking generalisation bounds to their chained counterparts, derived new bounds using Wasserstein distance.
result Chained generalisation bounds can be tighter than standard bounds, especially for concentrated hypothesis distributions.
With the help of a generalization of the Fermat principle in general relativity, we show that chains in CR geometry are geodesics of a certain Kropina metric constructed from the CR structure. We study the projective equivalence of Kropina metrics and show that if the kernel distributions of the corresponding 1-forms a…
In this work, we investigate a novel training procedure to learn a generative model as the transition operator of a Markov chain, such that, when applied repeatedly on an unstructured random noise sample, it will denoise it into a sample that matches the target distribution from the training set. The novel training pro…
We study the problem of detecting the presence of a single unknown spike in a rectangular data matrix, in a high-dimensional regime where the spike has fixed strength and the aspect ratio of the matrix converges to a finite limit. This setup includes Johnstone's spiked covariance model. We analyze the likelihood ratio …