arXiv research

Paper proposes a new method to minimize submodular functions with fewer calls to simpler oracles.

Discussion of ``2004 IMS Medallion Lecture: Local Rademacher complexities and oracle inequalities in risk minimization'' by V. Koltchinskii [arXiv:0708.0083]

Discussion of ``2004 IMS Medallion Lecture: Local Rademacher complexities and oracle inequalities in risk minimization'' by V. Koltchinskii [arXiv:0708.0083]

Discussion of ``2004 IMS Medallion Lecture: Local Rademacher complexities and oracle inequalities in risk minimization'' by V. Koltchinskii [arXiv:0708.0083]

Discussion of ``2004 IMS Medallion Lecture: Local Rademacher complexities and oracle inequalities in risk minimization'' by V. Koltchinskii [arXiv:0708.0083]

Discussion of "2004 IMS Medallion Lecture: Local Rademacher complexities and oracle inequalities in risk minimization" by V. Koltchinskii [arXiv:0708.0083]

Minimizing a function over an intersection of convex sets is an important task in optimization that is often much more challenging than minimizing it over each individual constraint set. While traditional methods such as Frank-Wolfe (FW) or proximal gradient descent assume access to a linear or quadratic oracle on the …

Improved Frank-Wolfe algorithm for constrained convex optimization with nearest extreme point oracle.

New algorithm learns efficiently with a simple 'yes/no' oracle.

New algorithm learns FMDP structure while minimizing regret.

Optimizes bilevel empirical risk minimization with improved oracle calls.

Piecewise polynomial interpolation-based gradient descent reduces oracle complexity for smooth loss functions.

New algorithms ensure reproducibility and optimal convergence in convex optimization.

Study on tradeoffs between mistakes and ERM oracle calls in online and transductive learning.

We investigate properties of estimators obtained by minimization of U-processes with the Lasso penalty in high-dimensional settings. Our attention is focused on the ranking problem that is popular in machine learning. It is related to guessing the ordering between objects on the basis of their observed predictors. We p…

Agghoo averages hold-out learning rules for theoretical and practical risk minimization.

A new method for creating derivatives without oracles.

Accelerates ERM problems with LPI-GD and improved oracle complexity.

New method solves constrained self-concordant minimization problems efficiently.

We provide tight upper and lower bounds on the complexity of minimizing the average of $m$ convex functions using gradient and prox oracles of the component functions. We show a significant gap between the complexity of deterministic vs randomized optimization. For smooth functions, we show that accelerated gradient de…

Study improves CTS's approximation regret for combinatorial bandits.

EP-learning framework improves causal contrast estimation efficiency.

We discuss the problem of adaptive discrete-time signal denoising in the situation where the signal to be recovered admits a "linear oracle" -- an unknown linear estimate that takes the form of convolution of observations with a time-invariant filter. It was shown by Juditsky and Nemirovski (2009) that when the $\ell_2…

New algorithm improves gradient-based ERM for smooth convex losses.

The paper analyzes prediction error in nonstationary settings using weighted risk minimization.

We analyze general model selection procedures using penalized empirical loss minimization under computational constraints. While classical model selection approaches do not consider computational aspects of performing model selection, we argue that any practical model selection procedure must not only trade off estimat…

Efficient estimator for two-sample functionals improves on oracle performance.

GPE algorithm optimizes nonparametric contextual bandits with efficient regret bounds.

Algorithm minimizes regret while adhering to unknown safety constraints.

Study on costs of manipulating AMM-based price oracles.

New algorithm reduces ERM problem size while maintaining accuracy.

The effect of errors in variables in quantization is investigated. We prove general exact and non-exact oracle inequalities with fast rates for an empirical minimization based on a noisy sample $Z_i=X_i+ε_i,i=1,\ldots,n$, where $X_i$ are i.i.d. with density $f$ and $ε_i$ are i.i.d. with density $η$. These rates depend …

The paper addresses contextual optimization problems with feedback, aiming to minimize regret.

Gradient descent is efficient for solving feasibility problems with minimal memory and queries.

Study on gradient complexity of private optimization with private oracles.

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

Oracle-efficient algorithm for offline RL with partial data coverage.

Paper establishes tight lower bounds for minimizing certain smooth and convex functions.

Optimizes personalized medicine prediction by individual tuning.

A new method for faster optimization of noisy functions.

New data-dependent priors improve PAC-Bayes bounds.

Paper tackles dynamic pricing in a geometrically decaying environment, achieving better occupancy with lower rates.

We consider the problem of binary classification where one can, for a particular cost, choose not to classify an observation. We present a simple proof for the oracle inequality for the excess risk of structural risk minimizers using a lasso type penalty.

The key issue in Dynamic Ensemble Selection (DES) is defining a suitable criterion for calculating the classifiers' competence. There are several criteria available to measure the level of competence of base classifiers, such as local accuracy estimates and ranking. However, using only one criterion may lead to a poor …

New algorithm tackles smooth online learning with optimal regret.

Improved algorithm finds second-order stationary points in non-convex optimization.

A new federated learning algorithm improves on existing methods by exploiting data smoothness.

We introduce an efficient algorithmic framework for model selection in online learning, also known as parameter-free online learning. Departing from previous work, which has focused on highly structured function classes such as nested balls in Hilbert space, we propose a generic meta-algorithm framework that achieves o…