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.

168,657 papers · 148 categories

Trend · papers per month

96192288384 · May 202619922001200920172026
48 results for H-consistency bound

Study of loss functions for learning to defer, proving consistency.

problem Learning to defer in machine learning.
method Introduced a family of surrogate losses parameterized by ΨΨ and proved their consistency.
result Proved realizable HH-consistency and Bayes-consistency of specific surrogate losses.

Enhanced HH-consistency bounds derived under relaxed conditions.

problem Quantifying the relationship between zero-one estimation error and surrogate loss estimation error.
method Relaxing the condition on the surrogate loss conditional regret and presenting a general framework for establishing enhanced HH-consistency bounds.
result Derivation of more favorable HH-consistency bounds in various scenarios.

Study on HH-consistency bounds for machine learning surrogates.

problem Estimating target loss error relative to surrogate loss error in machine learning.
method Developed HH-consistency bounds for various surrogates and loss functions.
result Stronger guarantees than existing methods, offering distribution-dependent and -independent bounds.

Enhanced consistency bounds derived for classification under a new noise condition.

problem Enhanced consistency bounds for classification under a new noise condition.
method Model Margin Noise (MM noise) assumption, derived enhanced H-consistency bounds.
result Enhanced H-consistency bounds under MM noise condition, interpolates between linear and square-root regimes.

This paper tackles deferral learning with multiple experts, providing strong theoretical guarantees.

problem Optimizing input assignment to experts balancing accuracy and computational cost.
method Introducing new surrogate loss functions and efficient algorithms with strong theoretical learning guarantees.
result Realizable HH-consistency, HH-consistency bounds, and Bayes-consistency for deferral learning.

Unified surrogate loss framework for multi-label learning with strong consistency guarantees.

problem Improving consistency and accounting for label correlations in multi-label learning.
method Introducing multi-label logistic loss and extending it to comprehensive multi-label comp-sum losses, proving strong consistency guarantees for any multi-label loss.
result Unified surrogate loss framework benefiting from strong consistency guarantees for any multi-label loss.

Study on top-kk classification with new loss functions and algorithms.

problem Improving multi-class classification accuracy and cardinality trade-off.
method Introducing cardinality-aware loss functions and deriving their consistency bounds.
result New cardinality-aware algorithms for top-kk classification.

Paper establishes a universal growth rate for smooth surrogate losses in classification.

problem Analyzing growth rates of consistency bounds for various surrogate losses.
method Proves square-root growth rate for smooth margin-based losses; extends to multi-class classification.
result Demonstrates a universal square-root growth rate for smooth comp-sum and constrained losses.

New method improves consistency in preference learning for neural networks.

problem Inconsistent surrogate losses in preference learning for neural networks.
method Formulated a margin-shifted ranking framework and introduced Structure-Aware HH-consistency.
result Proved superior consistency guarantees for capacity-bounded models using heavy-tailed surrogates.

Study of estimation errors in surrogate loss minimizers, providing stronger guarantees than existing methods.

problem Estimation errors in surrogate loss minimizers for various hypothesis sets.
method Detailed study of H\mathscr{H}-consistency estimation error bounds, proving general theorems for distribution-dependent and independent settings.
result Explicit bounds for zero-one and adversarial losses, showing enhancements under distributional assumptions.

Develops algorithms for optimizing multi-label metrics with provable guarantees.

problem Optimizing complex multi-label metrics like F-measure and Jaccard index.
method Principled learning algorithms based on H-consistency for generalized metrics.
result Provable HH-consistency bounds for multi-label metric optimization.

Study on learning to defer with multiple experts using new surrogate losses.

problem Learning to defer with multiple experts in a machine learning context.
method Introducing a new family of surrogate losses for the multiple-expert setting, proving HH-consistency bounds, and designing learning algorithms.
result Explicit guarantees for new learning to defer algorithms based on minimization of these surrogate losses.

New algorithms optimize metrics for binary classification with class imbalance.

problem Optimizing metrics like Fβ, AM, Jaccard for imbalanced classes.
method Reformulates metric optimization as cost-sensitive learning, using surrogate loss functions.
result METRO algorithms provide strong theoretical guarantees and outperform baselines.

Study on calibration and consistency of adversarial surrogate losses.

problem Designing robust classifiers with theoretical guarantees.
method Extensive analysis of H-calibration and H-consistency of adversarial surrogate losses.
result Some convex loss functions and supremum-based convex losses are not H-calibrated for important hypothesis sets.

This thesis tackles learning with multi-class abstention and multi-expert deferral, improving model reliability and efficiency.

problem Improving model reliability and efficiency in large language models (LLMs) by leveraging multiple experts.
method Developed new surrogate losses and consistency guarantees for multi-class classification and regression with deferral.
result Strong consistency guarantees for surrogate losses in multi-class classification and regression with deferral.

The paper revisits discriminative vs. generative classifiers, showing naive Bayes requires fewer samples.

problem Comparing discriminative and generative classifiers in multiclass settings.
method Theoretical analysis and simulations of naive Bayes vs. logistic regression.
result Multiclass naive Bayes requires fewer samples to approach asymptotic error compared to logistic regression.

Theoretical analysis of cross-entropy loss functions and their robustness.

problem Guarantees for using cross-entropy as a surrogate loss function.
method Theoretical analysis of a broad family of loss functions, including cross-entropy.
result First HH-consistency bounds for comp-sum losses and smooth adversarial comp-sum losses.

Given a hyperbolic subgroup HH of a hyperbolic group GG for which a Cannon-Thurston map $\hat i:\partial H \ra \partial G$ exists, we study the limit set ΛHΛ_H of HH with respect to its action on G\partial G. We prove that the set of conical limit points is exactly the subset of ΛHΛ_H consisting of the points to wh…

2013-01-15abs ↗pdf ↗

A new method for learning to defer decisions with expert advice improves over standard methods.

problem Learning to defer decisions with expert advice in systems where expert information can be modified after selection.
method An augmented surrogate that operates on the composite expert-advice action space, providing consistency guarantees and excess-risk bounds.
result The method improves over standard Learning-to-Defer and adapts its advice acquisition behavior to the cost regime.

Unified RMOT framework for non-modelable risk factors reduces audit bounds.

problem Infinite audit bounds for exotic derivatives pricing with sparse market data.
method Rough Martingale Optimal Transport (RMOT) with rough volatility regularization.
result Finite, explicit, and asymptotically tight extrapolation bounds for non-modelable risk factors.

Let G/HG/H be a compact homogeneous space, and let g^0\hat{g}_0 and g^1\hat{g}_1 be GG-invariant Riemannian metrics on G/HG/H. We consider the problem of finding a GG-invariant Einstein metric gg on the manifold G/H×[0,1]G/H\times [0,1] subject to the constraint that gg restricted to G/H×{0}G/H\times \{0\} and G/H×{1}G/H\times \{1\} co…

2017-10-05abs ↗pdf ↗

Linear-Core Surrogates combine fast optimization and statistical efficiency in classification and structured prediction.

problem The trade-off between smoothness and margin-based losses in classification and structured prediction.
method Linear-Core (LC) Surrogates, a family of convex loss functions that stitch a linear core to a smooth tail.
result LC Surrogates achieve fast linear consistency rates while maintaining differentiability and strict HH-consistency bounds.

Online L2D algorithm for multiclass classification with varying experts.

problem Handling streaming data, changing expert availability, and shifting expert distribution.
method First online L2D algorithm with O((n+ne)T2/3)O((n+n_e)T^{2/3}) and O((n+ne)T)O((n+n_e)\sqrt{T}) regret guarantees.
result Effective extension of standard L2D to settings with varying expert availability and reliability.

A novel framework for regression with multiple experts, addressing challenges in infinite and continuous label spaces.

problem Challenges in regression with multiple experts due to the infinite and continuous nature of the label space.
method Introduces a novel framework for regression with deferral, analyzing both single-stage and two-stage scenarios with new surrogate loss functions.
result Proves HH-consistency bounds for both single-stage and two-stage methods, providing stronger guarantees than Bayes consistency.

We study Tian's αα-invariant in comparison with the α1α_1-invariant for pairs (Sd,H)(S_d,H) consisting of a smooth surface SdS_d of degree dd in the projective three-dimensional space and a hyperplane section HH. A conjecture of Tian asserts that α(Sd,H)=α1(Sd,H)α(S_d,H)=α_1(S_d,H). We show that this is indeed true for d=4d=4 (the res…

2015-08-17abs ↗pdf ↗

We introduce spherical T-duality, which relates pairs of the form (P,H)(P,H) consisting of a principal SU(2)SU(2)-bundle PMP\rightarrow M and a 7-cocycle HH on PP. Intuitively spherical T-duality exchanges HH with the second Chern class c2(P)c_2(P). Unless dim(M)4dim(M)\leq 4, not all pairs admit spherical T-duals and the spheric…

2014-05-22abs ↗pdf ↗

The holonomy algebra $\g$ of an n+2n+2-dimensional Lorentzian manifold (M,g)(M,g) admitting a parallel distribution of isotropic lines is contained in the subalgebra $\simil(n)=(\Real\oplus\so(n))\zr\Real^n\subset\so(1,n+1)$. An important invariant of $\g$ is its $\so(n)$-projection $\h\subset\so(n)$, which is a Riemannian…

2010-01-25abs ↗pdf ↗

Let TT be a circle and LTLT be its loop group. Let M\mathcal{M} be an infinite dimensional manifold equipped with a nice LTLT-action. We construct an analytic LTLT-equivariant index for M\mathcal{M}, and justify it in terms of noncommutative geometry. More precisely, we construct a Hilbert space H\mathcal{H} consis…

2017-01-21abs ↗pdf ↗

New framework for learning from imbalanced data with theoretical guarantees.

problem Class imbalance in machine learning, especially in multi-class problems.
method Theoretical framework and new margin loss function for imbalanced classification.
result Proves strong HH-consistency of the proposed margin loss function.

Study of groups and their quasi-isometrically embedded subgroups.

problem Understanding the structure and properties of groups and their subgroups.
method Abstracting the notion of A/QI triples and using methods from geometric group theory.
result Stability of quasi-isometrically embedded subgroups in finitely generated groups.

In earlier papers, we introduced spherical T-duality, which relates pairs of the form (P,H)(P,H) consisting of an oriented S3S^3-bundle PMP\rightarrow M and a 7-cocycle HH on PP called the 7-flux. Intuitively, the spherical T-dual is another such pair (P^,H^)(\hat P, \hat H) and spherical T-duality exchanges the 7-flux with …

2015-02-16abs ↗pdf ↗

The paper studies a special Grassmannian space and shows it's an orbit of a unitary group.

problem Investigating a specific Grassmannian space of infinite-dimensional subspaces.
method Analyzing the restricted pp-Schatten class Grassmannian and showing it's an affine coadjoint orbit of a unitary group.
result The restricted pp-Schatten class Grassmannian is shown to be an affine coadjoint orbit of an infinite-dimensional restricted unitary group.

The paper classifies differentiable structures on a line with two origins.

problem Classifying differentiable structures on a non-Hausdorff line with two origins.
method Using homeomorphisms and diffeomorphisms, the paper establishes a bijection between structures and coset classes.
result The line with two origins admits uncountably many non-diffeomorphic structures for each differentiability class.

Unified framework for deferring queries to top-k experts, improving accuracy-cost trade-offs.

problem Limitation of existing L2D frameworks to single-expert deferral.
method Top-kk Learning-to-Defer framework, including adaptive Top-k(x)k(x) variant.
result Superior accuracy-cost trade-offs with multi-expert deferral.

Let TT be a circle group, and LTLT be its loop group. We hope to establish an index theory for infinite-dimensional manifolds which LTLT acts on, including Hamiltonian LTLT-spaces, from the viewpoint of KKKK-theory. We have already constructed several objects in the previous paper \cite{T}, including a Hilbert space $…

2017-09-18abs ↗pdf ↗

The study optimizes bounds for comparing training and population loss.

problem Optimizing bounds for comparing training and population loss.
method Derives generic information-theoretic and PAC-Bayesian generalization bounds using convex comparator functions.
result The tightest possible bound is obtained with the comparator being the convex conjugate of the CGF of the bounding distribution.

Paper improves PAC-Bayes bounds for various loss types.

problem Improving PAC-Bayes bounds for different types of losses.
method Introducing new high-probability PAC-Bayes bounds for bounded and general tail behaviors losses, and extending to anytime-valid bounds.
result New fast-rate and mixed-rate bounds for losses with bounded ranges, and parameter-free bounds for losses with general tail behaviors.

Improved bounds for Monte Carlo Rademacher Averages using self-bounding functions.

problem Proving sharper concentration bounds for MCERA.
method Deriving new bounds through self-bounding functions and concentration of measure.
result Novel bounds depend on data-dependent quantities, improving over standard methods.