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.

169,341 papers · 148 categories

Trend · papers per month

7.7%15.3%23.0%30.6% · Jun 202019922001200920182026
48 results for L2 optimization

L2 regularization loses its effect with batch normalization.

problem L2 regularization's effectiveness is undermined by batch normalization.
method Theoretical and experimental investigation of L2 regularization's interaction with batch normalization.
result L2 regularization's regularizing effect is eliminated when combined with batch normalization.

The problem of joint feature selection across a group of related tasks has applications in many areas including biomedical informatics and computer vision. We consider the l2,1-norm regularized regression model for joint feature selection from multiple tasks, which can be derived in the probabilistic framework by assum…

2012-05-09abs ↗pdf ↗

Optimal L2 extension theorem for holomorphic vector bundles with singular metrics.

problem Establishing conditions for optimal L2 extension in complex geometry.
method Analyzing singular Nakano positivity and applying L2 extension theorem.
result Necessary condition for equality in optimal L2 extension theorem.

A standing conjecture in L2-cohomology is that every finite CW-complex X is of L2-determinant class. In this paper, we prove this whenever the fundamental group belongs to a large class of groups containing e.g. all extensions of residually finite groups with amenable quotients, all residually amenable groups and free …

1998-07-07abs ↗pdf ↗

L2-Boosting fails to recover sparse parameters in high-dimensional models.

problem Theoretical differences between L2-Boosting and L1-penalized methods like Lasso.
method Proof of theoretical property differences between L2-Boosting and L1-penalized methods.
result L2-Boosting does not guarantee parameter recovery in high-dimensional models.

For a normal covering over a closed oriented topological manifold we give a proof of the L2-signature theorem with twisted coefficients, using Lipschitz structures and the Lipschitz signature operator introduced by Teleman. We also prove that the L-theory isomorphism conjecture as well as the C^*_max-version of the Bau…

2002-09-13abs ↗pdf ↗

Study L2-transverse conformal Killing forms on foliated manifolds.

problem Prove vanishing theorems for L2-transverse conformal Killing forms.
method Analyzes L2-transverse conformal Killing forms on complete foliated Riemannian manifolds and Kahler foliations.
result Proves vanishing theorems for L2-transverse conformal Killing forms.

New framework assesses regularization norms in ill-posed problems, revealing L2 instability and proposing adaptive fractional RKHS solutions.

problem Comparative analysis of regularization norms in ill-posed problems.
method Small noise analysis framework for Tikhonov and RKHS regularizations.
result Optimal convergence rates achieved with adaptive fractional RKHS, but hyper-parameters decay too fast.

New theoretical framework improves error rates for sparse learning with convex regularization.

problem Improving error rates for sparse learning with convex regularization.
method Proposed a new theoretical framework using common assumptions to derive high-dimensional estimation bounds.
result Improved error rates for L1, Slope, and Group L1-L2 regularizations, matching or exceeding existing results.

We provide a proof for an inequality between volume and L2-Betti numbers of aspherical manifolds for which Gromov outlined a strategy based on general ideas of Connes. The implementation of that strategy involves measured equivalence relations, Gaboriau's theory of L2-Betti numbers of R-simplicial complexes, and other …

2006-05-23abs ↗pdf ↗

We give a topological interpretation of the space of L2-harmonic forms on finite-volume manifolds with sufficiently pinched negative curvature. We give examples showing that this interpretation fails if the curvature is not sufficiently pinched and that our result is sharp with respect to the pinching constants. The me…

2002-07-12abs ↗pdf ↗

Robust algorithm identifies sparse signals using L2 regularization.

problem Reconstructing sparse signals from noisy data using overcomplete dictionaries.
method Corrected Projections Algorithm (CPA) with L2 regularization.
result CPA efficiently identifies known atoms in noisy signals.

New stochastic CG algorithm with variance reduction converges faster and is more efficient.

problem Optimization of linear and nonlinear problems, especially in machine learning.
method Stochastic Conjugate Gradient (CG) algorithm with variance reduction.
result The algorithm converges faster and is more efficient than existing methods.

In this paper, we study the evolution of L2 p-forms under Ricci flow with bounded curvature on a complete non-compact or a compact Riemannian manifold. We show that under curvature pinching conditions on such a manifold, the L2 norm of a smooth p-form is non-increasing along the Ricci flow. The L^{\infty} norm is showe…

2007-01-15abs ↗pdf ↗

Study ablated data augmentation techniques and their mathematical equivalence to penalties.

problem Lack of mathematical understanding of differences between ablated data augmentation techniques.
method Formal model of mean ablated data augmentation and inverted dropout for linear regression; empirical validation for deep networks.
result Ablated data augmentation and inverted dropout are mathematically equivalent to penalties in optimization.

Study on L2-boosting behavior as learning rate approaches zero.

problem Understanding the asymptotic behavior of L2-boosting algorithms with vanishing learning rates.
method Analyzes L2-boosting for regression with linear base learners, proving a deterministic limit and characterizing it as a solution to a linear differential equation.
result Proves the existence of a unique solution to the limit problem and analyzes the training and test error.

Study shows pre-event L2 liquidity state predicts crypto futures liquidity better than event labels.

problem Understanding how crypto futures liquidity changes over time.
method Combining L2 order book data, trade-flow records, and macro-event windows to define discrete liquidity-state transitions and evaluate models.
result Pre-event L2 liquidity state predicts post-event liquidity regimes better than event labels, and order flow adds value only when layered on top of the state model.

New characterizations of curvature operators for specific forms via L2-estimates.

problem Characterizing semi-positive and semi-negative curvature operators for (n,q)(n,q) and (p,n)(p,n)-forms.
method Using L2-estimates to characterize curvature operators for (n,q)(n,q) and (p,n)(p,n)-forms.
result New characterizations of Nakano semi-positivity and semi-negativity.

In this paper, we establish various L2-estimates for the exterior differential operator on p-convex Riemannian manifolds in the sense of Harvey and Lawson. As geometric applications, we prove vanishing and finiteness results for the de Rham cohomology groups.

2013-05-15abs ↗pdf ↗

We study a policy gradient method with L2 regularization for MAB problems.

problem Improving policy gradient methods for MAB problems with regularization.
method Investigate convergence of a policy gradient algorithm with L2 regularization for MAB.
result Prove convergence under appropriate technical hypotheses and show practical improvements.

This study investigates the impact of importance weighting in deep learning models.

problem Understanding the effect of importance weighting in deep neural networks.
method The study uses theoretical and empirical approaches to analyze the behavior of importance weighting in deep learning models.
result Importance weighting impacts models early in training but diminishes over successive epochs in deep neural networks.

The choice of the kernel is critical to the success of many learning algorithms but it is typically left to the user. Instead, the training data can be used to learn the kernel by selecting it out of a given family, such as that of non-negative linear combinations of p base kernels, constrained by a trace or L1 regular…

2012-05-09abs ↗pdf ↗

Two new methods improve block-sparse signal recovery from noisy data.

problem Recovering block-sparse signals with unknown partitions.
method LogLOP-l2/l1 and AdaLOP-l2/l1 methods using log-sum penalty and MCP.
result Our methods outperform existing techniques in estimation accuracy.

Dropout is one of the key techniques to prevent the learning from overfitting. It is explained that dropout works as a kind of modified L2 regularization. Here, we shed light on the dropout from Bayesian standpoint. Bayesian interpretation enables us to optimize the dropout rate, which is beneficial for learning of wei…

2014-12-22abs ↗pdf ↗

For one-parameter degenerations of compact Kähler manifolds, we determine the asymptotic behavior of the first Chern form of the direct image of a Nakano semi-positive vector bundle twisted by the relative canonical bundle, when the direct image is equipped with the L2-metric.

2010-07-16abs ↗pdf ↗

In the previous papers \cite{L1, L2} the author constructed Mabuchi and Aubin-Yau functionals over any complex surfaces and three-folds, respectively. Using the method in \cite{L2}, we construct those functionals over any complex manifolds of the complex dimension bigger than or equal to 2.

2010-04-05abs ↗pdf ↗

We show that the Novikov-Shubin invariant of an element of the integral group ring of the lamplighter group Z_2 \wr Z can be irrational. This disproves a conjecture of Lott and Lueck. Furthermore we show that every positive real number is equal to the Novikov-Shubin invariant of some element of the real group ring of Z…

2010-09-01abs ↗pdf ↗