The Knowledge Gradient (KG) policy was originally proposed for online ranking and selection problems but has recently been adapted for use in online decision making in general and multi-armed bandit problems (MABs) in particular. We study its use in a class of exponential family MABs and identify weaknesses, including …
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
48 results for “gradient index selection”
Paper improves Lasso for S&P500 index tracking with post-selection inference.
problem Index tracking for S&P500 with many applications.
method Used Lasso for dimension reduction and post-selection inference.
result Lasso method for S&P500 index tracking shows high performance.
A new FL algorithm reduces communication overhead by selectively updating model parameters.
problem Data heterogeneity and communication overhead in federated learning.
method Uses age of information metric to selectively update model parameters and group clients with similar data.
result Our method can expedite training and surpass other communication-efficient strategies in efficiency.
The paper studies implicit regularization in over-parameterized models for high-dimensional data.
problem Understanding implicit regularization in over-parameterized models for high-dimensional data.
method The paper designs regularization-free algorithms for the high-dimensional single index model and provides theoretical guarantees for the induced implicit regularization phenomenon.
result The proposed methods achieve minimax optimal statistical rates of convergence and outperform classical methods with explicit regularization.
Stochastic gradient descent (SGD) is the workhorse of modern machine learning. Sometimes, there are many different potential gradient estimators that can be used. When so, choosing the one with the best tradeoff between cost and variance is important. This paper analyzes the convergence rates of SGD as a function of ti…
Asset pre-selection for a cardinality constrained index tracking portfolio with optional enhancementq-fin.PM
The paper optimizes asset selection for index trackers and enhanced trackers with varying cardinality constraints.
problem Optimizing asset selection for index trackers and enhanced trackers with cardinality constraints.
method Divided into two steps: asset pre-selection and asset weight estimation. Used eight pre-selection procedures with different combinations of selection methods and regression types.
result Out-of-sample tracking errors are roughly proportional to 1/sqrt(cardinality). OLS is more effective than LAD, BE marginally more effective than FS, and (n) marginally more effective than (c).
Configuration spaces for computer systems can be challenging for traditional and automatic tuning strategies. Injecting task-specific knowledge into the tuner for a task may allow for more efficient exploration of candidate configurations. We apply this idea to the task of index set selection to accelerate database wor…
Local constancy of index for certain gradient mappings proved.
problem Proving the local constancy of the index for specific gradient mappings.
method Using a more general theorem for quasiregular gradient mappings, deducing the result from the Hessian's properties.
result The index is locally constant for functions with uniformly positive determinant Hessian almost everywhere.
Flexible deep learning framework controls FDR for feature selection.
problem Controlling Type-I error in feature selection for deep neural networks.
method Approximates FDR control for a wide range of deep architectures using gradient-based feature-importance vectors.
result Theoretical guarantee of FDR control for feature selection in deep learning models.
Machine learning predicts US stock market crashes.
problem Early detection of stock market crises.
method Random Forest and Extreme Gradient Boosting models.
result Extreme Gradient Boosting outperforms other models.
Why Indexing Worksq-fin.PM
We develop a simple stock selection model to explain why active equity managers tend to underperform a benchmark index. We motivate our model with the empirical observation that the best performing stocks in a broad market index often perform much better than the other stocks in the index. Randomly selecting a subset o…
Gradient descent dynamics studied for DEQs in linear and single-index models.
problem Understanding gradient descent dynamics for DEQs.
method Rigorously studied gradient descent dynamics for DEQs in linear and single-index models.
result Gradient descent converges to a global minimizer for linear DEQs and single-index models.
Develops methods to calculate global index of real polynomials.
problem Calculating the global index of real polynomials.
method Two methods: via atypical fibres and Milnor arcs clusters.
result Derives upper bounds for the global index, refining Durfee's degree-based bound.
Abstract reviews algorithms for multi-index models, focusing on polynomial-time methods and their limitations.
problem Estimating the index space in multi-index models efficiently and accurately.
method Polynomial-time algorithms in Gaussian space, nonparametric gradient estimation, and neural network fitting.
result A gap exists between computationally efficient methods and information-theoretical minimum.
New Morse theory techniques glue nontransverse flowlines.
problem Gluing nontransverse gradient flowlines in Morse theory.
method Adapted OBG techniques from Hutchings and Taubes to Morse theory.
result Explicit criteria for gluing certain flowlines.
In this paper we consider an interval portfolio selection problem with uncertain returns and introduce an inclusive concept of satisfaction index for interval inequality relation. Based on the satisfaction index, we propose an approach to reduce the interval programming problem with uncertain objective and constraints …
The proximal inertial gradient descent is efficient for the composite minimization and applicable for broad of machine learning problems. In this paper, we revisit the computational complexity of this algorithm and present other novel results, especially on the convergence rates of the objective function values. The no…
DFR models dynamic distributional data with weighted Fréchet means.
problem Regression of distribution-valued responses over time.
method Dynamic Fréchet Regression (DFR) with index-aware weighting and feature selection.
result Improved predictive accuracy and feature recovery over existing methods.
Paper compares feature selection methods using GCM and LOCO, showing GCM methods generally outperform LOCO.
problem Feature selection and importance estimation in model-agnostic settings.
method Comparison of feature selection methods related to GCM and LOCO under three model settings.
result GCM-related methods generally outperform LOCO under suitable regularity conditions, as shown by theoretical and empirical results.
Gradient flow solves multi-index regression for high-dimensional Gaussian data.
problem Learning multi-index functions from high-dimensional Gaussian data.
method Two-timescale algorithm with non-parametric link function learning.
result Global convergence of Grassmannian population gradient flow dynamics.
Understanding the influence of features in machine learning is crucial to interpreting models and selecting the best features for classification. In this work we propose the use of principles from coalitional game theory to reason about importance of features. In particular, we propose the use of the Banzhaf power inde…
New EI strategies using OWA and SSD for excess return.
problem Selecting EI portfolios that stochastically dominate a benchmark.
method Proposes a new OWA-based EI model and introduces a new SSD criterion.
result OWA-based EI portfolios stochastically dominate a benchmark and generate excess return.
This paper selects features in deep neural networks with theoretical guarantees.
problem Feature selection in deep neural networks with unknown nonlinear functions.
method Reformulate neural networks as index models, estimate feature sets using Stein's formula, and apply screening-and-selection mechanism.
result Consistent feature selection with theoretical guarantees, even in high-dimensional settings.
Investigates nearly Kähler and parallel G2 manifolds using Hitchin functionals.
problem Stability analysis of nearly Kähler and parallel G2 manifolds.
method Gradient flow of Hitchin functionals, spectral decomposition of Hessians, Hitchin index.
result Hitchin index provides a lower bound for the Einstein co-index.
Gini index needs auto-calibration for consistent decision-making.
problem Gini index's inconsistency in decision-making.
method Restrict Gini index to auto-calibrated regression models.
result Gini index becomes strictly consistent with auto-calibration.
Estimates linear models from self-selected data, addressing econometric challenges.
problem Estimating linear models from self-selected data with known or unknown selection criteria.
method Developed efficient algorithms for both known and unknown selection criteria.
result Identified and estimated linear models from self-selected data, accommodating various selection criteria.
New algorithm finds best subset in high-dimensional data models.
problem Finding the best subset of predictors in high-dimensional data models.
method Proposes a scalable algorithm using a generalized information criterion.
result Directly proves consistency and oracle property for the best-subset selection.
A gradient-based variable selection for binary classification in reproducing kernel Hilbert spacestat.ML
Proposes a gradient-based variable selection method for binary classification in RKHS.
problem Variable selection in high-dimensional data analysis.
method Gradient-based representation of large-margin classifier with group-lasso penalty.
result Selection consistency and risk bound of the estimated classifier.
Theorems on the existence of vector fields with given sets of Indexes of isolated Singular points are proved for the cases of closed manifolds, pairs of manifolds, manifolds with boundary, and gradient fields. It is proved that, on a two-dimensional manifold, an index of an isolated Singular point of the gradient field…
We generalize a method by L. Ambrozio, A. Carlotto, and B. Sharp to study the Morse index of closed f-minimal hypersurfaces isometrically immersed in a general weighted manifold. The technique permits, in particular, to obtain a linear lower bound on the Morse index via the first Betti number for closed f-minimal hyper…
Near a birth-death critical point in a one-parameter family of gradient flows, there are precisely two Morse critical points of index difference one on the birth side. This paper gives a self-contained proof of the folklore theorem that these two critical points are joined by a unique gradient trajectory up to time-shi…
Robust Transformer-Based One-Step Stock Index Forecasting via Shifted Data Augmentation
problem Robust stock index forecasting
method Modified Transformer architecture with Shifted Data Augmentation
result Best performance on benchmark datasets
Gradient-like flows on certain manifolds restrict saddle Morse indices to 1 or n-1.
problem Restricting Morse indices of saddles in gradient-like flows.
method Analyzing invariant manifolds and their intersections for gradient-like flows.
result Morse indices of saddles are either 1 or n-1, no other indices possible.
Heavy-tailed distributions emerge in SGD's parameter evolution.
problem Understanding heavy-tailed distributions in SGD parameter evolution.
method Continuous diffusion approximation of SGD (homogenized SGD) analysis.
result Explicit upper and lower bounds on tail-index of homogenized SGD.
The paper uses TDA to select stocks for a sparse portfolio, improving performance across market scenarios.
problem Sparse portfolio selection in financial markets.
method Topological data analysis (TDA) for clustering stock price movements.
result The TDA-based clustering strategy significantly enhances sparse portfolio performance.
The paper proves continuity of Morse index for Ricci shrinkers.
problem Lower and upper semi-continuity of the Morse index for gradient Ricci shrinkers.
method Adapting and refining recent arguments on CMC hypersurfaces and polynomially weighted Sobolev spaces, with techniques for non-compact shrinkers.
result Identifies a condition ensuring the Morse index of asymptotically conical shrinkers is bounded below by the f-index of their asymptotic cone.
Full-batch GD outperforms one-pass SGD in learning a single-index model with quadratic activation.
problem Learning a single-index model with quadratic activation using gradient descent.
method Full-batch gradient descent compared to one-pass stochastic gradient descent (SGD) on a correlation loss.
result Full-batch GD requires only samples for strong recovery, while one-pass SGD requires samples.
Convolutional neural networks (CNNs) achieve state-of-the-art performance in a wide variety of tasks in computer vision. However, interpreting CNNs still remains a challenge. This is mainly due to the large number of parameters in these networks. Here, we investigate the role of compression and particularly pruning fil…
New framework limits SGD for multi-index models, addressing SQ framework shortcomings.
problem Limitations of SGD for multi-index models beyond SQ framework.
method Developed a new non-SQ framework to study SGD limitations for single-index and multi-index models.
result Applies to broad settings and architectures, including neural networks.
Variable selection and dimension reduction are two commonly adopted approaches for high-dimensional data analysis, but have traditionally been treated separately. Here we propose an integrated approach, called sparse gradient learning (SGL), for variable selection and dimension reduction via learning the gradients of t…
New algorithm maintains privacy while improving model performance in selective release.
problem Privacy degradation and slow convergence in DPSGD.
method Differentially Private Selective Release based on Clipped Gradients (DPSR-CG).
result Maintains strict privacy guarantees while achieving exceptional model performance.
Hybrid Policy Optimization tackles reinforcement learning in hybrid spaces, improving performance over PPO.
problem Credit assignment issues and biased gradients in hybrid discrete-continuous action spaces.
method Mixed gradient estimator combining pathwise and score-function gradients, reformulating problems in hybrid form.
result HPO substantially outperforms PPO on inventory control and switched systems, with performance gaps increasing with continuous action dimension.
SGD shows distinct phases in learning single-index models, achieving optimal sample complexity and regret.
problem Learning single-index models with SGD in adaptive data settings.
method Stochastic gradient descent (SGD) with an optimal learning rate schedule.
result SGD achieves near-optimal sample complexity and regret guarantees across both burn-in and learning phases.
Learning single index model with gradient descent: spectral initialization and precise asymptoticsmath.ST
This work analyzes a two-stage algorithm for single index models, showing precise asymptotics of gradient descent.
problem Learning single index models with non-convex optimization.
method Spectral initialization followed by gradient descent, with detailed analysis of dynamics and asymptotics.
result Gradient descent converges to long-time fixed points in the large system limit, representing mean field behavior.
On fitting the Pareto-Levy distribution to stock market index data: selecting a suitable cutoff valuecond-mat.other
The so-called Pareto-Levy or power-law distribution has been successfully used as a model to describe probabilities associated to extreme variations of worldwide stock markets indexes data and it has the form from empirical d…
Generalized Exponentiated Gradient Algorithms and Their Application to On-Line Portfolio Selectioncs.LG
EGAB algorithms improve online portfolio selection.
problem Online portfolio selection problem.
method Generalized exponentiated gradient (EG) updates with Alpha-Beta divergence regularization.
result EGAB algorithms enhance portfolio performance, especially with transaction costs.
New neural networks learn single-index models efficiently.
problem Learning low-dimensional structure in high-dimensional data.
method Shallow neural networks with frozen biases, studied via gradient flow.
result Generalization guarantees match near-optimal sample complexity.
GSSBO reduces GP fitting time in Bayesian optimization.
problem High computational cost of fitting Gaussian process surrogate models in Bayesian optimization.
method Gradient-based sample selection to reduce the number of samples used in GP fitting.
result Sublinear regret bounds and significant reduction in computational cost.