New algorithms for efficient reinforcement learning with rich observations.
problem Efficient reinforcement learning with rich observations in environments with deterministic dynamics.
method Oracle-efficient algorithms using standard optimization primitives.
result Proved sample efficiency and presented examples of challenges.
New measure mitigates algorithmic discrimination in rich class of computations.
problem Discrimination in algorithmic predictions due to data analysis biases.
method Develops multicalbration, a new measure of algorithmic fairness.
result Multicalibration guarantees accurate predictions for every subpopulation.
Implicit Policy simplifies complex reinforcement learning policies.
problem Complex action distributions in reinforcement learning.
method Rich policy class with entropy regularization.
result Entropy regularization with rich policy class achieves desirable properties.
Transformers capture combinatorial tasks with bounded error and logarithmic sample dependence.
problem Capturing complex combinatorial tasks with bounded error and sample efficiency.
method Formal definition of algorithmic capture, empirical analysis of infinite-width transformers, upper bounds on computational complexity.
result Transformers exhibit an inductive bias favoring simpler algorithmic procedures over higher complexity ones.
We study recursive-cube-of-rings (RCR), a class of scalable graphs that can potentially provide rich inter-connection network topology for the emerging distributed and parallel computing infrastructure. Through rigorous proof and validating examples, we have corrected previous misunderstandings on the topological prope…
New reservoir computing approach handles infinite-dimensional systems.
problem Approximating and generalizing complex input/output systems.
method Randomly generated echo state networks with neural networks.
result Proves universal approximation properties for new class of systems.
We propose a black-box variational inference method to approximate intractable distributions with an increasingly rich approximating class. Our method, termed variational boosting, iteratively refines an existing variational approximation by solving a sequence of optimization problems, allowing the practitioner to trad…
MEDL_CVAE learns complex correlations among multiple entities using rich context.
problem Learning complex correlations among multiple entities with rich context.
method Conditional Variational Auto-Encoder (CVAE) for encoding conditional multivariate distributions.
result MEDL_CVAE captures rich dependency structures and improves joint likelihood.
Implicit models can match or exceed explicit models with more test-time compute.
problem Understanding the expressive power and scaling of implicit models.
method Nonparametric analysis of expressive power, mathematical characterization of implicit operators, and test-time scaling experiments.
result Implicit models can progressively express more complex mappings through iteration, matching a richer function class with test-time compute.
Method learns latent states from rich observations to improve RL exploration.
problem Improving RL performance with rich observations and latent states.
method Estimates latent states from observations through regression and clustering, providing finite-sample guarantees.
result Exponential improvement over Q-learning with naïve exploration. Neural networks learn discrete tasks on continuous data via emergent geometry.
problem Understanding how neural networks perform discrete computations on continuous data.
method Analysis of Riemannian pullback metric across neural network layers.
result Neural networks learn to discretize continuous inputs and perform logical operations on these discretized variables.
Optimal testing framework for many experiments with costly observations.
problem Optimal testing in scenarios with many hypotheses and limited observations.
method Characterized and computed the optimal policy for sampling experiments, developed a heuristic.
result High-powered classical tests can be inefficient in the experiment-rich regime.
New method learns SDEs without integrators, speeding up computation.
problem Computational expense in learning SDEs using neural networks.
method Importance-sampling estimator for SDEs, leveraging parallelism.
result Lower-variance gradient estimates and massive computation time reductions.
Extends structured prediction to continuous manifold valued regression.
problem Continuous manifold valued regression problems.
method Geometric optimization for manifold valued regression.
result Statistical consistency of the proposed approach.
We introduce a new and rich class of graph coloring manifolds via the Hom complex construction of Lovasz. The class comprises examples of Stiefel manifolds, series of spheres and products of spheres, cubical surfaces, as well as examples of Seifert manifolds. Asymptotically, graph coloring manifolds provide examples of…
Improved Gaussian process models for interpretable predictions.
problem Complex responses require high-dimensional interaction terms in additive Gaussian processes.
method Orthogonal additive kernel (OAK) with orthogonality constraint on additive functions.
result OAK models achieve similar or better predictive performance with fewer terms, retaining interpretability.
A computational model for the distribution of wealth among the members of an ideal society is presented. It is determined that a realistic distribution of wealth depends upon two mechanisms: an asymmetric flux of wealth in trading transactions that advantages the poorer of the two traders and a non-stationary creation …
New insights on stability in reservoir computing for better performance.
problem Stability in reservoir computing networks.
method Using the recurrent kernel limit for large reservoir sizes.
result Quantitative characterization of stability and chaos frontier.
Study shows computational and statistical gaps in Gaussian Single-Index Models.
problem Statistical and computational trade-offs in high-dimensional regression problems.
method Analysis of SQ and LDP frameworks, partial-trace algorithm.
result Computational algorithms require significantly more samples than information-theoretic limits.
New findings on hyperbolicity of fine curve graphs and their subgraphs.
problem Investigating hyperbolicity of fine curve graphs and their subgraphs.
method Analyzing large subgraphs of fine curve graphs and computing distances in specific cases.
result Large subgraphs of fine curve graphs contain flats of every finite dimension, indicating they are not hyperbolic.
We present an exploration of the rich theoretical connections between several classes of regularized models, network flows, and recent results in submodular function theory. This work unifies key aspects of these problems under a common theory, leading to novel methods for working with several important models of inter…
Study shows zero Pontrjagin classes for sprays.
problem Characterization of locally projectively flat metrics.
method Analysis of Pontrjagin classes for sprays.
result Manifolds with locally projectively flat metrics have zero Pontrjagin classes.
Empirical study on rich subgroup fairness for machine learning.
problem Ensuring fairness across large subgroups in machine learning.
method An algorithm that learns subject to rich subgroup fairness constraints.
result Rich subgroup fairness leads to large gains in fairness with mild accuracy costs.
Associated with isoparametric foliations of unit spheres, there are two classes of minimal surfaces − minimal isoparametric hypersurfaces and focal submanifolds. By virtue of their rich structures, we find new series of minimizing cones. They are cones over focal submanifolds and cones over suitable products among th…
Researchers develop Malliavin calculus for signatures, simplifying option Greeks computation.
problem Lack of tractability and explicit representations in Malliavin calculus.
method Focus on finite linear combinations of time-extended Brownian motion signatures, derive explicit formulas for Malliavin derivative, and compute Greeks for path-dependent options.
result Closed-form expressions for classical operators of Malliavin calculus, providing algebraic formulations.
Bispectral OT improves dataset comparison by preserving intrinsic coherence.
problem Ignoring intrinsic coherence in dataset comparisons using pairwise geometric distances.
method Introduces Bispectral Optimal Transport, a symmetry-aware extension of discrete OT.
result Transport plans computed with Bispectral OT achieve greater class preservation accuracy.
Machine learning disciplines shift values, not just model types.
problem Values influence machine learning discipline and model types.
method Philosophy of science lens, conceptual framework analysis.
result Disciplinary shifts encode social and political values.
Recent advances in stochastic gradient variational inference have made it possible to perform variational Bayesian inference with posterior approximations containing auxiliary random variables. This enables us to explore a new synthesis of variational inference and Monte Carlo methods where we incorporate one or more s…
In a general and non metrical framework, we introduce the class of CR quaternionic manifolds containing the class of quaternionic manifolds, whilst in dimension three it particularizes to, essentially, give the conformal manifolds. We show that these manifolds have a rich natural Twistor Theory and, along the way, we o…
This study reveals efficient finite-difference computation for gradient regularization in deep learning.
problem Improving generalization performance in deep learning through gradient regularization.
method Analyzes and reveals a specific finite-difference computation that reduces computational cost and improves generalization performance.
result Finite-difference computation strengthens the implicit bias towards rich regimes and enhances generalization performance.
In a general and non metrical framework, we introduce the class of co-CR quaternionic manifolds, which contains the class of quaternionic manifolds, whilst in dimension three it particularizes to give the Einstein-Weyl spaces. We show that these manifolds have a rich natural Twistor Theory and, along the way, we obtain…
A new method for density estimation using nearest neighbor Dirichlet mixtures.
problem Slow and unstable Bayesian density estimation methods.
method Nearest neighbor grouping, local Bayesian parametric models, Dirichlet prior, Monte Carlo sampling.
result Effective density estimation with improved computational efficiency.
New metric measures dynamical richness without relying on accuracy.
problem Lack of a reliable metric for measuring dynamical richness.
method Developed a computationally efficient, performance-independent metric based on low-rank bias.
result Metric recovers neural collapse as a special case and captures known transitions without accuracy.
A deep learning approach for fitting complex distributions.
problem Limited applicability of simple kernels in fitting complex distributions.
method Learning a deep network to parameterize the kernel of the exponential family.
result The method can fit complex structures on moderate-dimensional problems.
Adversarial meta-learning computes Gamma-minimax estimators for vague prior knowledge.
problem Estimating parameters with vague prior knowledge.
method Adversarial meta-learning algorithms for Gamma-minimax estimators.
result Convergence guarantees and neural network class for selection.
Survey discusses new ideas in geometric group theory and their applications.
problem Understanding geodesic metric spaces and their equivariant wall structures.
method Introduces and highlights the impact of injective metric spaces and cubical approximation theorem.
result Rich equivariant wall structures in various geodesic metric spaces.
Study minimax optimal RL in factored MDPs with bonus exploration.
problem Optimal reinforcement learning in episodic factored MDPs.
method Proposes two model-based algorithms with bonus exploration for minimax optimal regret.
result Achieves minimax optimal regret guarantees for rich factored structures.
HOMER learns latent states to explore rich environments efficiently.
problem Exploration in rich observation environments with unknown latent states.
method Interleaves representation learning and strategic exploration to identify kinematic states.
result Provably efficient exploration with polynomial sample complexity in latent states and time horizon.
Polynomial-time algorithm finds planted hypercube vectors in Gaussian mixtures.
problem Clustering d-dimensional Gaussian mixtures with unknown covariance.
method Lattice-based methods using Lenstra--Lenstra--Lovasz reduction.
result Achieves statistically-optimal sample complexity of d+1 samples.
Paper introduces models to discover complex structures in large hypergraphs.
problem Understanding dependency structures in complex systems represented as hypergraphs.
method Probabilistic models treating classes of similar units as nodes in a latent hypergraph, using low-rank representations.
result Improves link prediction and discovers interpretable structures in diverse real-world systems.
In this paper we investigate the relationship between isotopy classes of knots and links in S^3 and the diffeomorphism types of homeomorphic smooth 4-manifolds. As a corollary of this initial investigation, we begin to uncover the surprisingly rich structure of diffeomorphism types of manifolds homeomorphic to the K3 s…
Statistical detection of a rare class of objects in a two-class classification problem can pose several challenges. Because the class of interest is rare in the training data, there is relatively little information in the known class response labels for model building. At the same time the available explanatory variabl…
Latent variable models are an elegant framework for capturing rich probabilistic dependencies in many applications. However, current approaches typically parametrize these models using conditional probability tables, and learning relies predominantly on local search heuristics such as Expectation Maximization. Using te…
Spherically symmetric metrics form a rich and important class of metrics. Many well-known Finsler metrics of constant flag curvature can be locally expressed as a spherically symmetric metric on R^n. In this paper, we study spherically symmetric metrics with constant Ricci curvature and constant flag curvature.
We provide an exact solution to the ideal-gas-like models studied in econophysics to understand the microscopic origin of Pareto-law. In these class of models the key ingredient necessary for having a self-organized scale-free steady-state distribution is the trading or collision rule where agents or particles save a d…
New fractal spaces not quasisymmetric to Loewner spaces discovered.
problem Finding new fractal spaces not quasisymmetric to Loewner spaces.
method Introduced iterated graph systems (IGS) to create new fractal spaces.
result Disproved Kleiner's conjecture about self-similar fractals.
We investigate the effect of tax evasion on the income distribution and the inequality index of a society through a kinetic model described by a set of nonlinear ordinary differential equations. The model allows to compute the global outcome of binary and multiple microscopic interactions between individuals. When evas…
This work concerns the definition and analysis of a new class of Lie systems on Poisson manifolds enjoying rich geometric features: the Lie--Hamilton systems. We devise methods to study their superposition rules, time independent constants of motion and Lie symmetries, linearisability conditions, etc. Our results are i…