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.

168,742 papers · 148 categories

Trend · papers per month

13253850 · May 202619922001200920172026
48 results for Marginal-Conditioned Bridges

A new sampler for FLMs improves token-level decoding controls.

problem Sampling from FLMs using standard methods collapses marginals and produces invalid sequences.
method Samples clean one-hot endpoints from FLM token marginals and uses Ornstein-Uhlenbeck bridges conditioned on these endpoints.
result The method preserves token-wise posterior-predictive marginals and improves quality-diversity tradeoff.

3MSBM learns smooth trajectories from multiple snapshots.

problem Capturing long-range temporal dependencies in complex systems.
method Lifts dynamics to phase space, generalizes stochastic bridges to multi-marginal conditional problems, learns transport maps preserving intermediate marginals.
result Significantly improves convergence and scalability in capturing complex dynamics.

Neural networks can approximate high-dimensional classifiers with ReLU networks under margin conditions.

problem Approximating high-dimensional discontinuous classifiers with neural networks.
method Using ReLU neural networks with three hidden layers, approximating a classifier with a Barron-regular decision boundary.
result High-dimensional discontinuous classifiers can be approximated with a rate of n1n^{-1} under strong margin conditions.

Study minimax rates for binary classifier estimation with margin conditions.

problem Estimating binary classifiers with geometric margin conditions.
method Derive lower bounds for worst-case learning rates over various function classes.
result Identify optimal rates close to O(n1)\mathcal{O}(n^{-1}) for different function classes.

Study shows exponential error reduction in multiclass classification without bias-variance trade-off.

problem Multiclass classification with margin conditions.
method Analysis of classification error under hard-margin conditions.
result Exponential decrease in classification error without bias-variance trade-off.

Risk bounds for Classification and Regression Trees (CART, Breiman et. al. 1984) classifiers are obtained under a margin condition in the binary supervised classification framework. These risk bounds are obtained conditionally on the construction of the maximal deep binary tree and permit to prove that the linear penal…

2009-02-18abs ↗pdf ↗

Active learning can't improve over passive in certain settings.

problem Active learning vs. passive learning in nonparametric settings.
method Analyzing margin conditions and their effects on active learning performance.
result Nuances in margin conditions determine whether active learning can outperform passive learning.

Researchers expand on best subset selection theory, identifying key complexities.

problem Understanding model selection performance in high-dimensional sparse linear regression.
method Analyzing residualized signals, orthogonality, and spurious projections to establish margin conditions.
result Established necessary and sufficient margin conditions for BSS model consistency.

Develops a Best-of-Both-Worlds algorithm for linear contextual bandits with Tsallis entropy.

problem Linear contextual bandits with i.i.d. contexts.
method Follow-The-Regularized-Leader (FTRL) with Tsallis entropy.
result Achieves $O\left(\log(T)^{\frac{1+β}{2+β}}T^{\frac{1}{2+β}} ight)$ regret under margin condition.

New test for conditional independence using GNNs avoids estimating conditional distributions.

problem Testing conditional independence of XX and YY given ZZ.
method Proposes a non-parametric testing procedure using GNNs to sample from marginal conditional distributions.
result Test statistic is doubly robust against GNN approximation errors.

Proposes methods to identify and estimate counterfactual distributions with confounding.

problem Estimating counterfactual distributions in the presence of confounding.
method Nonparametric identification and semiparametric estimation using conditional copulas and machine learning.
result Valid inference for individual-level effects and nonparametric identifiability of latent confounding subspace.

A new policy learning method allows policies to abstain when uncertain, improving safety and applicability.

problem Risk of making decisions without full confidence in uncertain predictions.
method Policy learning with abstention, identifying near-optimal policies and constructing an abstention rule.
result Improved safety and applicability in policy learning, with theoretical guarantees.

Empirical risk minimization (ERM) is a fundamental learning rule for statistical learning problems where the data is generated according to some unknown distribution P\mathsf{P} and returns a hypothesis ff chosen from a fixed class F\mathcal{F} with small loss \ell. In the parametric setting, depending upon $(\ell…

2014-06-14abs ↗pdf ↗

This paper is devoted to the bipartite ranking problem, a classical statistical learning task, in a high dimensional setting. We propose a scoring and ranking strategy based on the PAC-Bayesian approach. We consider nonlinear additive scoring functions, and we derive non-asymptotic risk bounds under a sparsity assumpti…

2015-11-09abs ↗pdf ↗

Post-training optimizes model performance beyond base model limits.

problem Optimizing sequence prediction models beyond the base model's support.
method Policy gradient (PG) and adaptive learning rate (LR) techniques.
result Post-training with PG can achieve near-optimal performance beyond the base model's support.

We consider the stochastic contextual bandit problem with additional regularization. The motivation comes from problems where the policy of the agent must be close to some baseline policy which is known to perform well on the task. To tackle this problem we use a nonparametric model and propose an algorithm splitting t…

2018-10-11abs ↗pdf ↗

The paper provides examples of keen weakly reducible bridge spheres for links in b-bridge position.

problem Characterizing and finding examples of keen weakly reducible bridge spheres.
method Analyzing bridge spheres and their properties in terms of compressing disks and width complex.
result Infinitely many examples of keen weakly reducible bridge spheres for links in b-bridge position.

Suppose a knot in a 33-manifold is in nn-bridge position. We consider a reduction of the knot along a bridge disk DD and show that the result is an (n1)(n-1)-bridge position if and only if there is a bridge disk EE such that (D,E)(D, E) is a cancelling pair. We apply this to an unknot KK, in nn-bridge position with re…

2016-06-23abs ↗pdf ↗

Determinantal point processes (DPPs) are elegant probabilistic models of repulsion that arise in quantum physics and random matrix theory. In contrast to traditional structured models like Markov random fields, which become intractable and hard to approximate in the presence of negative correlations, DPPs offer efficie…

2012-07-25abs ↗pdf ↗

We show that if KK is a knot in S3S^3 and ΣΣ is a bridge sphere for KK with high distance and 2n2n punctures, the number of perturbations of KK required to interchange the two balls bounded by ΣΣ via an isotopy is nn. We also construct a knot with two different bridge spheres with 2n2n and 2n12n-1 bridges respecti…

2009-08-25abs ↗pdf ↗

Paper explores link and plat presentations, showing equivalence under bridge isotopy.

problem Relationship between links in bridge position and plat presentations.
method Established equivalence between Hilden double coset classes of plat presentations and bridge positions up to isotopy.
result Revealed equivalence of Hilden double coset classes for n-bridge unknot and torus knots in plat position.

For any given number of crossings cc, there exists a formula to determine the number of 2-bridge knots of cc crossings, and indeed it is a simple matter to actually construct presentations of these knots. However, the determination of whether a given (prime) knot is a 2-bridge knot remains a nontrivial exercise, and …

2004-09-20abs ↗pdf ↗

The purpose of this note is to announce complete answers to the following questions. (1) For an essential simple loop on a 2-bridge sphere in a 2-bridge link complement, when is it null-homotopic in the link complement? (2) For two distinct essential simple loops on a 2-bridge sphere in a 2-bridge link complement, when…

2011-04-18abs ↗pdf ↗