Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

50100150200 · May 202619922001200920172026
48 results for entropy preserving

In this paper we discuss Perelman's Lambda-functional, Perelman's Ricci shrinker entropy as well as the Ricci expander entropy on a class of manifolds with isolated conical singularities. On such manifolds, a singular Ricci de Turck flow preserving the isolated conical singularities exists by our previous work. We prov…

2019-02-06abs ↗pdf ↗

Survey on Ricci flow on spaces with conical singularities.

problem Analyzing Ricci flow on spaces with isolated conical singularities.
method Ricci de Turck flow preserving conical singularities, stability of Ricci flat metrics, preservation of positive scalar curvature under certain conditions.
result Ricci flat metrics with isolated conical singularities are stable and positive scalar curvature is preserved under the flow.

Paper introduces entropy for Riemannian foliations and connects it to Ricci flow.

problem Entropy functional for Riemannian foliations and its relation to Ricci flow.
method Introduced entropy functional and related its gradient flow to transverse Ricci flow.
result Entropy functional is monotonic along transverse Ricci flow and related to it.

Study reveals failure of uniqueness in dynamical invariants for 3D volume-preserving diffeomorphisms.

problem Uniqueness of dynamical invariants for 3D volume-preserving diffeomorphisms.
method Examined failure of uniqueness on integral homology spheres and arbitrary three-manifolds using local and global invariants.
result Failure of uniqueness is severe, with continuous and non-constant invariants appearing in C1C^1-open sets of nonvanishing exact fields of fixed helicity.

Study of Kähler-Ricci flow on toric Fano varieties with preserved symplectic condition.

problem Analyzing the generalized Kähler-Ricci flow on toric Fano varieties.
method Establishing global existence, deriving entropy and energy functionals.
result Convergence of nonsingular solutions at infinity and weak convergence of the flow.

Study Goeritz groups of link decompositions, focusing on their asymptotic behavior.

problem Understanding the asymptotic behavior of Goeritz groups for link decompositions.
method Defined Goeritz groups for link decompositions, analyzed their properties, and discussed their asymptotic behavior.
result Discussed the asymptotic behavior of minimal pseudo-Anosov entropies and related it to Goeritz groups of Heegaard splittings.

Entrocraft addresses RL performance saturation in LLMs by customizing entropy curves.

problem Performance saturation in RL algorithms for LLMs.
method Entrocraft uses rejection sampling to bias advantage distributions for customized entropy schedules.
result Entrocraft significantly improves generalization, output diversity, and long-term training in 4B models.

A new framework describes dissipation using a metriplectic 4-bracket.

problem Describing dissipation in a way that preserves energy and entropy.
method Using a metriplectic 4-bracket, a quantity like the Poisson bracket with symmetries motivated by Riemannian curvature.
result The metriplectic 4-bracket dynamics includes all known previous binary bracket theories for dissipation.

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…

2011-11-11abs ↗pdf ↗

Geodesic flows on compact manifolds without conjugate points are shown to have a unique measure of maximal entropy.

problem Analyzing geodesic flows on compact manifolds without conjugate points and with visibility universal covering.
method Using topological mixing, local product structure, and properties of geodesic flows, the authors prove the existence of an expansive factor and uniqueness of measure of maximal entropy.
result The geodesic flow on compact manifolds without conjugate points has a unique measure of maximal entropy.

Proposes an accuracy-preserving calibration method for DNNs.

problem Calibration of deep neural networks (DNNs) to measure prediction reliability.
method Uses Concrete distribution on the probability simplex to calibrate DNNs without accuracy loss.
result The proposed method outperforms previous methods in accuracy-preserving calibration tasks.

ALIEN improves uncertainty estimation of language models by refining entropy-based methods.

problem Overconfidence in uncertainty estimation for language models, especially for difficult inputs.
method ALIEN refines entropy-based uncertainty by aligning it with prediction reliability, using a lightweight uncertainty head.
result ALIEN consistently outperforms strong baselines in detecting incorrect predictions and achieving the lowest calibration error.

Geodesic flows on certain surfaces are shown to be semi-conjugate to expansive flows.

problem Understanding geodesic flows on compact surfaces without conjugate points.
method Time-preserving semi-conjugation to a continuous expansive flow.
result Geodesic flows on compact surfaces without conjugate points of genus > 1 have a unique measure of maximal entropy.

A quantum state generation method that respects physical constraints.

problem Generating quantum states with complex-valued Hermitian, positive semi-definite, and trace one properties.
method Mirror diffusion model with von Neumann entropy to enforce structural constraints.
result Demonstrated effective generation of quantum states with conditional guidance.

The study establishes a curvature-dimension condition for discrete Markov chains.

problem Proving modified logarithmic Sobolev inequalities for discrete Markov chains.
method Identifying and proving a curvature-dimension inequality CDΥ(κ,)CD_Υ(κ,\infty), and showing its compatibility with diffusive settings.
result The CDΥCD_Υ condition preserves curvature bounds under tensorization and leads to Beckner inequalities.

This work enhances collaborative inference privacy by minimizing conditional entropy and boosting robustness against model inversion attacks.

problem Privacy leakage in collaborative inference systems via model inversion attacks.
method Theoretical proof and derivation of a differentiable measure for bounding conditional entropy, followed by a CEM algorithm to maximize it.
result Theoretical proof and experimental validation show that CEM consistently boosts inversion robustness without compromising feature utility or efficiency.

This work addresses two main issues of the standard Kernel Entropy Component Analysis (KECA) algorithm: the optimization of the kernel decomposition and the optimization of the Gaussian kernel parameter. KECA roughly reduces to a sorting of the importance of kernel eigenvectors by entropy instead of by variance as in K…

2016-03-09abs ↗pdf ↗

The paper studies entropy calibration in language models and finds that miscalibration improves slowly with scale.

problem The problem is whether language model entropy calibration improves with scale and if it's possible to calibrate without reducing log loss.
method The authors study a simplified theoretical setting to characterize miscalibration scaling behavior and measure it empirically in language models ranging from 0.5B to 70B parameters.
result The observed scaling behavior of miscalibration is similar to theoretical predictions, indicating slow improvement with scale. The authors also prove theoretically that it is possible to reduce entropy while preserving log loss if access to a black box predicting future entropy is available.

Despite its well-known shortcomings, kk-means remains one of the most widely used approaches to data clustering. Current research continues to tackle its flaws while attempting to preserve its simplicity. Recently, the \textit{power kk-means} algorithm was proposed to avoid trapping in local minima by annealing throu…

2020-01-10abs ↗pdf ↗

A pseudo-Anosov surface automorphism φφ has associated to it an algebraic unit λφλ_φ called the dilatation of φφ. It is known that in many cases λφλ_φ appears as the spectral radius of a Perron-Frobenius matrix preserving a symplectic form LL. We investigate what algebraic units could potentially appear as dilatatio…

2011-04-13abs ↗pdf ↗

We introduce two new functionals on Sasaki manifolds, inspired by the work of Perelman, which are monotonic along the Sasaki-Ricci flow. We relate their gradient flow, via diffeomorphisms preserving the foliated structure of the manifold, to the transverse Ricci flow. Finally, when the basic first Chern class is positi…

2011-03-29abs ↗pdf ↗

The paper introduces submodular information measures for machine learning applications.

problem Generalizing information-theoretic measures to non-random variables.
method Developing combinatorial information measures based on submodular functions.
result Submodular mutual information is submodular in one argument for certain submodular functions.

Study improves summarization reliability in risky scenarios.

problem Reliability of automatic summarization in high-risk contexts.
method Conditional generation with Bayesian inference and entropy regularization.
result Significant improvement in robustness and reliability of summarization.

A new measure of causal influence quantifies intrinsic contributions in DAGs.

problem Quantifying intrinsic causal contributions in Directed Acyclic Graphs (DAGs).
method Recursive decomposition of node contributions, structure-preserving interventions, Shapley symmetrization.
result A measure of intrinsic causal contribution that is invariant to node relabeling.

New CVs preserve transition rates in molecular dynamics.

problem Designing CVs that accurately capture rare events in high-dimensional systems.
method Integrating manifold learning and group-invariant featurization to construct neural network-based CVs that satisfy orthogonality conditions.
result Achieved a CV for butane that reproduces the anti-gauche transition rate with less than ten percent relative error.

We propose a novel node embedding of directed graphs to statistical manifolds, which is based on a global minimization of pairwise relative entropy and graph geodesics in a non-linear way. Each node is encoded with a probability density function over a measurable space. Furthermore, we analyze the connection between th…

2019-05-24abs ↗pdf ↗

Bayesian neural networks learn efficiently at infinite width, matching polynomial-width performance.

problem Understanding the inductive bias of infinite-width neural networks.
method Analyzing the reduced entropy and using subsampling techniques.
result The Bayesian mean-field learner generalizes exactly on polynomially-bounded targets.

We obtain a compactness result for Fano manifolds and Kähler Ricci flows. Comparing to the more general Riemannian versions by Anderson and Hamilton, in this Fano case, the curvature assumption is much weaker and is preserved by the Kähler Ricci flows. One assumption is the boundedness of the Ricci potential and the ot…

2014-04-15abs ↗pdf ↗

Unified geometric flows improve deep learning efficiency and simplify neural network topologies.

problem Improving deep learning performance and simplifying neural network structures.
method Proposes a thermodynamically coupled Ricci flow that dynamically adapts parameter space geometry to loss landscape topology, enabling automated singularity resolution and providing entanglement entropy bounds.
result Demonstrates 2.1× convergence acceleration and 63% topological simplification while maintaining O(NlogN)\mathcal{O}(N\log N) complexity, outperforming Riemannian baselines by 15.2% in few-shot accuracy.