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

2675348001,067 · Jun 202019922001200920172026
48 results for Generic stabilizers

Paper relaxes stability and generalization assumptions for SGD.

problem Stability and generalization for SGD under restrictive assumptions.
method Introduces on-average model stability and develops novel bounds.
result First-ever-known fast bounds in low-noise setting using stability approach.

The study identifies conditions under which algorithmic stability explains generalization in interpolating learning systems.

problem Understanding when algorithmic stability explains generalization in interpolating learning systems.
method Modeling training as a function-space trajectory and measuring sensitivity to single-sample perturbations.
result There exist interpolating regimes with small risk where contractive sensitivity cannot hold, showing that stability is not a universal explanation.

New stability criteria for Fano varieties using generalized b-divisors.

problem Characterizing uniform KK-stability in Fano varieties.
method Introducing a new function ildeδ ildeδ and formalism for KK-stability, proving stability conditions for Kähler-Einstein metrics.
result Existence of a unique Kähler-Einstein metric implies uniform D\mathbf{D}-log KK-stability when ildeδ(D)>1 ildeδ(\mathbf{D}) > 1.

Study stabilizers of complex hyperbolic triangle groups, finding generators and signatures.

problem Understanding the stabilizers of complex hyperbolic triangle groups.
method Explicit generators and signatures of stabilizers computed for each group orbit of mirrors.
result Explicit generators and signatures of stabilizers for some triangle groups.

Proves finitely generated associated graded rings for valuations on log Fano pairs.

problem Stability thresholds of log Fano pairs.
method Proves finite generation of associated graded rings for valuations.
result Log Fano pairs are uniformly K-stable if their stability threshold is less than a certain value.

Equivalence proven between divisorial stability and quotient log divisorial stability.

problem Equivalence of divisorial stability and log divisorial stability under finite group actions.
method Interpolation technique and equivariant divisorial stability construction.
result Equivariant divisorial stability of a polarized variety is equivalent to log divisorial stability of its quotient.

The paper relaxes the stability condition to boost confidence in generalization for randomized learning algorithms.

problem The tension between uniform stability and L2L_2-stability in generalization bounds.
method Establishes in-expectation first moment generalization error bounds for L2L_2-stable randomized learning algorithms and uses subbagging to achieve near-tight exponential bounds.
result Improves generalization bounds for convex and non-convex optimization problems with SGD.

Paper analyzes stability and generalization of SCO algorithms.

problem Understanding how SCO algorithms perform on unseen data.
method Algorithmic stability analysis in statistical learning theory.
result Derives dimension-independent excess risk bounds for SCGD and SCSC.

Paper proposes a new framework to improve stability-based bounds in deep learning.

problem Explaining generalization in overparameterized neural networks.
method Decomposes excess risk dynamics into signal and noise components, applying stability-based bounds only to the noise.
result The decomposition framework improves stability-based bounds and explains generalization in neural networks.

New stability framework relaxes boundedness assumptions for generalization bounds.

problem Overly restrictive assumptions for modern learning settings with heavy-tailed or unbounded losses.
method Develops a stability-based framework requiring only finite LpL_p moment conditions.
result Sharp generalization bounds derived for various learning paradigms.

We explore in some detail the notion of algorithmic stability as a viable framework for analyzing the generalization error of learning algorithms. We introduce the new notion of training stability of a learning algorithm and show that, in a general setting, it is sufficient for good bounds on generalization error. In t…

2012-12-12abs ↗pdf ↗

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.

The paper explores the generalization of quantum neural networks using stability theory.

problem Understanding the generalization properties of quantum neural networks.
method The authors use algorithmic stability to establish generalization bounds for quantum neural networks.
result The paper provides practical insights into the design and training of quantum neural networks.

The paper extends stabilization methods to Poincaré Duality complexes.

problem Stabilization of Poincaré Duality complexes and homotopy gyrations.
method Develops new methods for stabilization of Poincaré Duality complexes, including a homotopy theoretic generalization of a gyration.
result Shows there are only finitely many possible homotopy types of gyrations for a fixed Poincaré Duality complex.

This work explores the trade-offs between stability and accuracy in statistical estimation.

problem Understanding the statistical cost of algorithmic stability.
method Statistical decision-theoretic perspective, focusing on worst-case and average-case stability.
result Optimal stable estimators for mean estimation and regression settings are developed, revealing trade-offs between stability and accuracy.

There is accumulating evidence in the literature that stability of learning algorithms is a key characteristic that permits a learning algorithm to generalize. Despite various insightful results in this direction, there seems to be an overlooked dichotomy in the type of stability-based generalization bounds we have in …

2019-03-12abs ↗pdf ↗

The paper explores stability and generalization of deep GCNs.

problem Understanding the stability and generalization of deep GCNs from a theoretical perspective.
method Theoretical analysis of stability and generalization properties of deep GCNs.
result The stability and generalization of deep GCNs are influenced by the maximum absolute eigenvalue of the graph filter operators and the depth of the network.

Paper analyzes stability and forgetting in score-based generative models.

problem Understanding the stability and long-time behavior of generative models.
method Quantitative bounds on sampling error using stability and forgetting properties of the Markov chain.
result Provides practical consequences of stability and contraction mechanism in sampling.

Boosting framework for vector-valued prediction with geometric stability.

problem Lack of a general theoretical understanding of aggregation for structured prediction.
method Identifies (α,β)(α,β)-stability property and proposes a boosting framework based on exponential reweighting and geometric-median aggregation.
result Obtains exponential decay of empirical divergence error under weak learner condition and (α,β)(α,β)-stability.

The paper analyzes stability and generalization of decentralized SGD.

problem Stability and generalization of decentralized stochastic gradient descent.
method Novel formulation of decentralized stochastic gradient descent combined with non/convex optimization theory.
result First stability and generalization guarantees for decentralized stochastic gradient descent.

The homology groups of many natural sequences of groups {Gn}n=1\{G_n\}_{n=1}^{\infty} (e.g. general linear groups, mapping class groups, etc.) stabilize as nn \rightarrow \infty. Indeed, there is a well-known machine for proving such results that goes back to early work of Quillen. Church and Farb discovered that many sequ…

2012-01-23abs ↗pdf ↗

Church-Ellenberg-Farb used the language of FI-modules to prove that the cohomology of certain sequences of hyperplane arrangements with S_n-actions satisfies representation stability. Here we lift their results to the level of the arrangements themselves, and define when a collection of arrangements is "finitely genera…

2016-03-28abs ↗pdf ↗

Studied how SGD's stability regularization affects generalization in neural networks.

problem Understanding why SGD often generalizes better than GD in neural networks.
method Analyzed stability of SGD and GD through Frobenius norm and trace of Hessian, and compared their generalization properties.
result Stable minima of SGD generalize well, while GD's stability-induced regularization is too weak.

Stacking is a general approach for combining multiple models toward greater predictive accuracy. It has found various application across different domains, ensuing from its meta-learning nature. Our understanding, nevertheless, on how and why stacking works remains intuitive and lacking in theoretical insight. In this …

2019-01-26abs ↗pdf ↗

We introduce a notion of algorithmic stability of learning algorithms---that we term \emph{argument stability}---that captures stability of the hypothesis output by the learning algorithm in the normed space of functions from which hypotheses are selected. The main result of the paper bounds the generalization error of…

2017-02-28abs ↗pdf ↗

Characterizes geometric actions on graphs with flexible stabilizers.

problem Understanding geometric actions on flexible stabilizers.
method Defining generalized fine actions and proving relative quasi-convexity criteria.
result Characterizes Bowditch boundary points in relatively geometric actions.

Define the 1-handle stabilization distance between two surfaces properly embedded in a fixed 4-dimensional manifold to be the minimal number of 1-handle stabilizations necessary for the surfaces to become ambiently isotopic. For every nonnegative integer mm we find a pair of 2-knots in the 4-sphere whose stabilization…

2019-08-19abs ↗pdf ↗

Uniform K-stability ensures existence of special metrics on toric manifolds.

problem Existence of conformally Kähler, Einstein-Maxwell metrics on toric manifolds.
method Introducing uniform K-stability and showing its equivalence to properness of relative K-energy.
result Uniform K-stability is necessary and sufficient for the existence of ff-extremal metrics on toric manifolds.

We find computable criteria for stability of symplectic leaves of Poisson manifolds. Using Poisson geometry as an inspiration, we also give a general criterion for stability of leaves of Lie algebroids, including singular ones. This not only extends but also provides a new approach (and proofs) to the classical stabili…

2008-10-24abs ↗pdf ↗

Inspired by convolutional neural networks on 1D and 2D data, graph convolutional neural networks (GCNNs) have been developed for various learning tasks on graph data, and have shown superior performance on real-world datasets. Despite their success, there is a dearth of theoretical explorations of GCNN models such as t…

2019-05-03abs ↗pdf ↗

In this article we develop a new approach to the problem of the stability of locally conformally Kähler structures (l.c.k structures) under small deformations of complex structures and deformations of flat line bundles. We show that under the certain cohomological condition the stability of l.c.k structures does hold. …

2010-12-10abs ↗pdf ↗

New bounds improve generalization in learning scenarios.

problem Limitations of existing information-theoretic bounds in SCO problems.
method Sample-conditioned hypothesis stability and neighboring-hypothesis matrix.
result Sharper generalization guarantees in various learning scenarios.

Paper proposes an unsupervised feature selection algorithm with stability guarantees.

problem Feature selection for dimension reduction and interpretability.
method Proposes a novel unsupervised feature selection algorithm with stability guarantees.
result The algorithm has superior generalization performance and stable selected features.

This paper extends stability analysis to non-convergent neural network training.

problem Generalization of neural networks whose training does not converge to fixed points.
method Introduces statistical algorithmic stability (SAS) to study non-convergent algorithms and their generalization.
result Stability of non-convergent training dynamics correlates with generalization performance.

In this article we introduce a higher dimensional analogue of Engel structure, motivated by the Cartan prolongation of contact manifolds. We study the stability of such structure, generalizing the Gray-type stability for Engel manifolds.

2018-08-23abs ↗pdf ↗

Stability is a general notion that quantifies the sensitivity of a learning algorithm's output to small change in the training dataset (e.g. deletion or replacement of a single training sample). Such conditions have recently been shown to be more powerful to characterize learnability in the general learning setting und…

2011-08-16abs ↗pdf ↗