Pages that link to "Item:Q675044"
From MaRDI portal
The following pages link to Exponentiated gradient versus gradient descent for linear predictors (Q675044):
Displaying 50 items.
- Adaptive regularization of weight vectors (Q374184) (← links)
- Adaptive and optimal online linear regression on \(\ell^1\)-balls (Q391734) (← links)
- Foraging theory for dimensionality reduction of clustered data (Q413822) (← links)
- Online variance minimization (Q420931) (← links)
- Weighted last-step min-max algorithm with improved sub-logarithmic regret (Q465257) (← links)
- A generalized online mirror descent with applications to classification and regression (Q493737) (← links)
- A continuous-time approach to online optimization (Q520967) (← links)
- Neural learning by geometric integration of reduced `rigid-body' equations (Q704191) (← links)
- Improved algorithms for online load balancing (Q831807) (← links)
- Adaptive stepsizes for recursive estimation with applications in approximate dynamic programming (Q851872) (← links)
- A primal-dual perspective of online learning algorithms (Q1009218) (← links)
- Competing with wild prediction rules (Q1009222) (← links)
- Learning to assign degrees of belief in relational domains (Q1009279) (← links)
- The Perceptron algorithm versus Winnow: linear versus logarithmic mistake bounds when few input variables are relevant (Q1127362) (← links)
- A game of prediction with expert advice (Q1271549) (← links)
- Worst-case analysis of the Perceptron and Exponentiated Update algorithms (Q1277700) (← links)
- Efficient learning with virtual threshold gates (Q1383714) (← links)
- Learning rotations with little regret (Q1689555) (← links)
- Scale-free online learning (Q1704560) (← links)
- A quasi-Bayesian perspective to online clustering (Q1786586) (← links)
- A kernel-based perceptron with dynamic memory (Q1943042) (← links)
- An efficient approach to solve the large-scale semidefinite programming problems (Q1955162) (← links)
- Dynamical memory control based on projection technique for online regression (Q1955472) (← links)
- Cutting-plane training of structural SVMs (Q1959520) (← links)
- Bayesian generalized probability calculus for density matrices (Q1959541) (← links)
- Extracting certainty from uncertainty: regret bounded by variation in costs (Q1959595) (← links)
- Analysis of two gradient-based algorithms for on-line regression (Q1970199) (← links)
- Relative utility bounds for empirically optimal portfolios (Q2040434) (← links)
- Achieving fairness with a simple ridge penalty (Q2080355) (← links)
- A modular analysis of adaptive (non-)convex optimization: optimism, composite objectives, variance reduction, and variational bounds (Q2290691) (← links)
- Constrained dual graph regularized orthogonal nonnegative matrix tri-factorization for co-clustering (Q2298773) (← links)
- Robust and sparse regression in generalized linear model by stochastic optimization (Q2303494) (← links)
- PAC-Bayesian risk bounds for group-analysis sparse regression by exponential weighting (Q2418515) (← links)
- Convergence of the exponentiated gradient method with Armijo line search (Q2420800) (← links)
- Recursive aggregation of estimators by the mirror descent algorithm with averaging (Q2432961) (← links)
- Regrets of proximal method of multipliers for online non-convex optimization with long term constraints (Q2679238) (← links)
- Prior knowledge and preferential structures in gradient descent learning algorithms (Q2782264) (← links)
- Limited Stochastic Meta-Descent for Kernel-Based Online Learning (Q3182496) (← links)
- PORTFOLIO SELECTION AND ONLINE LEARNING (Q3542654) (← links)
- RECURSIVE FORECAST COMBINATION FOR DEPENDENT HETEROGENEOUS DATA (Q3557552) (← links)
- The Concave-Convex Procedure (Q4408935) (← links)
- Competitive On-line Statistics (Q4831997) (← links)
- Out-of-Sample Utility Bounds for Empirically Optimal Portfolios in a Single-Period Investment Problem (Q5014532) (← links)
- Randomized Linear Programming Solves the Markov Decision Problem in Nearly Linear (Sometimes Sublinear) Time (Q5119845) (← links)
- Online Decision Making with High-Dimensional Covariates (Q5130496) (← links)
- Online Learning Based on Online DCA and Application to Online Classification (Q5131197) (← links)
- An entropic Landweber method for linear ill-posed problems (Q5210435) (← links)
- (Q5219717) (← links)
- Online Learning of Nash Equilibria in Congestion Games (Q5252509) (← links)
- Multiplicative Updates for Nonnegative Quadratic Programming (Q5440961) (← links)
