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.

168,982 papers · 148 categories

Trend · papers per month

236473709945 · Jun 202019922001200920172026
48 results for Condition Number Bounds

This work provides lower bounds for differentiable games and defines a new condition number.

problem Understanding the fundamental limits of convergence in differentiable games.
method The authors cast saddle-point and min-max problems as 2-player games and use tools from single-objective convex optimization to derive linear lower bounds for convex-concave games. They also introduce a new condition number for games.
result The authors provide linear lower bounds for differentiable games, including nn-player games, and introduce a new condition number that captures the possibility of linear rates in games without strong convexity or concavity.

We analyze the condition number of random feature matrices and prove their well-conditioned nature.

problem Understanding the condition number of random feature matrices and its impact on generalization error.
method Established concentration bounds and derived risk bounds for regression problems using random feature matrices.
result The risk associated with random feature matrices exhibits the double descent phenomenon, improving even with noise.

We give bounds on the number of non-simple closed curves on a negatively curved surface, given upper bounds on both length and self-intersection number. In particular, it was previously known that the number of all closed curves of length at most LL grows exponentially in LL. We get exponentially tighter bounds given…

2015-05-27abs ↗pdf ↗

New bounds for KRR condition number reveal overfitting phenomena.

problem Characterizing overfitting in KRR with varying kernel spectral decay.
method Derived new bounds for kernel matrices, enhanced test error bounds, and identified feature independence role.
result Identified tempered and catastrophic overfitting phenomena.

New algorithms learn GGMs without condition number bounds, even with strong dependencies.

problem Learning Gaussian Graphical Models without condition number bounds.
method Polynomial-time algorithms for attractive and walk-summable GGMs.
result Efficient recovery of graph structure with logarithmic number of samples.

We consider the following signal recovery problem: given a measurement matrix ΦRn×pΦ\in \mathbb{R}^{n\times p} and a noisy observation vector cRnc\in \mathbb{R}^{n} constructed from c=Φθ+εc = Φθ^* + ε where εRnε\in \mathbb{R}^{n} is the noise vector whose entries follow i.i.d. centered sub-Gaussian distribution, how to recover …

2013-04-30abs ↗pdf ↗

We give a simple unified proof for several disparate bounds on Thurston-Bennequin number for Legendrian knots and self-linking number for transverse knots in R^3, and provide a template for possible future bounds. As an application, we give sufficient conditions for some of these bounds to be sharp.

2007-09-13abs ↗pdf ↗

The study of special Lagrangian classes and semistable Mukai vectors on K3 surfaces.

problem Counting special Lagrangian classes and semistable Mukai vectors for K3 surfaces.
method Analyzing flat surfaces and K3 surfaces, using asymptotics and stability conditions.
result Exact leading term in the asymptotics of the number of semistable Mukai vectors.

Study on lens spaces bounding 4-manifolds with specific Betti numbers.

problem Which lens spaces can bound 4-manifolds with second Betti number one?
method Construction of specific 4-manifolds and analysis of lens space boundaries.
result Infinite families of lens spaces can bound 4-manifolds with second Betti number one, but not all.

The paper calculates Betti numbers for special geometric manifolds with curvature constraints.

problem Estimating Betti numbers for nearly G2G_2 and nearly Kähler manifolds with curvature bounds.
method Using Weitzenböck formulas and bounds on sectional curvature to estimate Betti numbers.
result Sufficient conditions for vanishing certain Betti numbers based on sectional curvature bounds.

Lower bounds found for nonconvex-strongly-concave min-max optimization problems.

problem Finding stationary points in nonconvex-strongly-concave min-max optimization.
method Provided lower bounds for first-order oracle complexity.
result Lower bounds of Ω(√κε⁻²) for deterministic oracles and Ω(√κε⁻² + κ¹/₃ε⁻⁴) for stochastic oracles.

For a given knot, we study the minimal number of positive eigenvalues of the double branched cover over spanning surfaces for the knot. The value gives a lower bound for various genera, the dealternating number and the alternation number of knots, and we prove that Batson's bound for the non-orientable 4-genus gives an…

2017-09-17abs ↗pdf ↗

The standard Bonnet-Myers theorem says that if the Ricci scalar of a Riemannian manifold is bounded below by a positive number, then the manifold is compact. Moreover, a bound of its diameter is pointed out. The theorem was extended to Finsler manifolds. In this paper we prove that if a certain condition on the average…

2014-05-22abs ↗pdf ↗

Smoothed analysis of complexity bounds and condition numbers has been done, so far, on a case by case basis. In this paper we consider a reasonably large class of condition numbers for problems over the complex numbers and we obtain smoothed analysis estimates for elements in this class depending only on geometric inva…

2006-05-24abs ↗pdf ↗

We study the spectrum of complete noncompact manifolds with bounded curvature and positive injectivity radius. We give general conditions which imply that their essential spectrum has an arbitrarily large finite number of gaps. In particular, for any noncompact covering of a compact manifold, there is a metric on the b…

2015-10-16abs ↗pdf ↗

Study affinely transverse foliations in sphere bundles, finding bounds and vanishing conditions.

problem Understanding affine transverse foliations in sphere bundles and their properties.
method Provided upper bounds for the Euler number and a new proof for vanishing conditions under amenable fundamental group.
result Upper bounds and vanishing conditions for the Euler number of sphere bundles.

In this paper, we will count the number of cusps of complete Riemannian manifolds MM with finite volume. When MM is a complete smooth metric measure spaces, we show that the number of cusps in bounded by the volume VV of MM if some geometric conditions hold true. Moreover, we use the nonlinear theory of the pp-Lap…

2017-04-01abs ↗pdf ↗

For any knot KK which bounds non-orientable and null-homologous surfaces FF in punctured nCP2n\mathbb{C}P^2, we construct a lower bound of the first Betti number of FF which consists of the signature of KK and the Heegaard Floer dd-invariant of the integer homology sphere obtained by 11-surgery along KK. By using …

2014-03-05abs ↗pdf ↗

Characterizes solutions to Z-critical equations on surfaces using effective conditions.

problem Characterizing solutions to Z-critical equations on compact Kähler surfaces.
method Uses effective conditions and Picard number bounds to characterize solutions.
result Characterizes optimally destabilizing curves for Donaldson's J-equation and deformed Hermitian Yang-Mills equation.

Study finds upper bounds for exotic options using call prices, converging with more data.

problem Finding consistent upper price bounds for exotic options with limited call price data.
method Model-free approach using martingale property of stock price process, focusing on directionally convex payoffs.
result Upper price bounds converge with more observed call prices, especially for directionally convex payoffs.

Improved mistake bound for group linear separable cases in online multiclass linear classification.

problem Improving mistake bounds for online multiclass linear classification under group linear separable conditions.
method Refined group weak linear separability condition and rational kernel approach.
result Achieved a mistake bound of K2ildeO(1/γlogL))K\cdot 2^{ ilde{O}(\sqrt{1/γ}\log L)}) under group weak linear separable condition.

Lower bounds on MALA and HMC for well-conditioned distributions.

problem Understanding the performance limits of Metropolized sampling methods.
method Analyzing the Metropolis-adjusted Langevin algorithm (MALA) and multi-step Hamiltonian Monte Carlo (HMC) with a leapfrog integrator.
result Nearly-tight lower bound of Ω~(κd)\widetildeΩ(κd) on the mixing time of MALA from an exponentially warm start.

The paper proves conditions for vanishing and estimating Betti numbers of Riemannian manifolds.

problem Vanishing and estimating Betti numbers of Riemannian manifolds with curvature constraints.
method Proves vanishing and estimation theorems for pextthp^{ ext{th}}-Betti numbers using curvature conditions.
result Vanishing of Betti numbers for 33-positive curvature operators in dimensions 5,65,6.

We give multiplicity results for the problem of prescribing the scalar curvature on Cauchy- Riemann spheres under Beta-flatness condition. To give a lower bound for the number of solutions, we use Bahri methods based on the theory of critical points at infinity and a Poincare-Hopf type formula.

2018-12-22abs ↗pdf ↗

We improve bounds for stochastic processes, especially those with heavy tails.

problem Bounding the concentration of sub-ψψ processes with heavy tails.
method Variational approach to concentration, focusing on sub-Gaussian and other tail conditions.
result First dimension-free self-normalized empirical Bernstein inequality.

The paper optimizes risk-sensitive RL with CVaR, achieving near-minimax-optimal results.

problem Optimizing risk-sensitive reinforcement learning with CVaR objective.
method Developed algorithms for multi-arm bandits and online RL in MDPs, achieving near-minimax-optimal regret.
result Achieved near-minimax-optimal regret of O(τ1SAK)O(τ^{-1}\sqrt{SAK}) for constant ττ.

Investigates portfolio optimization with and without gearing constraints.

problem Improving portfolio weights for better alignment with expected returns.
method Extends the alpha-weight angle bound to include gearing constraints and uses theoretical arguments and simulations.
result Equally weighted portfolios are not preferable to mean-variance portfolios even with poor forecast ability and a badly conditioned covariance matrix.

The condition number predicts efficient information encoding in neural units, aiding model fine-tuning.

problem Efficient information encoding in neural units for various tasks and input modalities.
method Linking the condition number to the log-volume scaling factor and entropy of the output distribution.
result High condition number indicates efficient encoding, reducing overall information transfer.

This paper provides a general result on controlling local Rademacher complexities, which captures in an elegant form to relate the complexities with constraint on the expected norm to the corresponding ones with constraint on the empirical norm. This result is convenient to apply in real applications and could yield re…

2015-10-06abs ↗pdf ↗

Efficiently estimates private least squares with linear error growth.

problem Private estimation of ordinary least squares with bounded residuals and leverage.
method Scaled noise added to a stable nonprivate estimator of the regression vector.
result Near-optimal accuracy guarantee with linear error growth in dimension.