scientific article; zbMATH DE number 7255066
From MaRDI portal
Publication:4969074
zbMATH Open1498.68225arXiv1901.02324MaRDI QIDQ4969074FDOQ4969074
Authors: Mathieu Blondel, André F. T. Martins, Vlad Niculae
Publication date: 5 October 2020
Full work available at URL: https://arxiv.org/abs/1901.02324
Title of this publication is not available (Why is that?)
Recommendations
- Learned-loss boosting
- Learning with varying insensitive loss
- Toward a unified approach to fitting loss models
- Learning without concentration for general loss functions
- On Bayesian learning via loss functions
- Learning with convex loss and indefinite kernels
- Large loss networks
- Optimal learning with Gaussians and correntropy loss
- An investigation for loss functions widely used in machine learning
Learning and adaptive systems in artificial intelligence (68T05) Analysis of algorithms and problem complexity (68Q25)
Cites Work
- A Fast Iterative Shrinkage-Thresholding Algorithm for Linear Inverse Problems
- Scikit-learn: machine learning in Python
- Graphical models, exponential families, and variational inference
- Title not available (Why is that?)
- Numerical Optimization
- Title not available (Why is that?)
- Strictly Proper Scoring Rules, Prediction, and Estimation
- Concerning nonnegative matrices and doubly stochastic matrices
- In defense of one-vs-all classification
- Robust Estimation of a Location Parameter
- Error bounds for convolutional codes and an asymptotically optimum decoding algorithm
- On the limited memory BFGS method for large scale optimization
- A shortest augmenting path algorithm for dense and sparse linear assignment problems
- Smooth minimization of non-smooth functions
- Information and exponential families in statistical theory
- VC theory of large margin multi-category classifiers
- Dynamic programming algorithm optimization for spoken word recognition
- A primal-dual convergence analysis of boosting
- A kernel two-sample test
- Title not available (Why is that?)
- Clustering with Bregman divergences.
- Title not available (Why is that?)
- Title not available (Why is that?)
- Convex Analysis
- Title not available (Why is that?)
- Sparse Reconstruction by Separable Approximation
- Possible generalization of Boltzmann-Gibbs statistics.
- Title not available (Why is that?)
- Generalization of Shannon–Khinchin Axioms to Nonextensive Systems and the Uniqueness Theorem for the Nonextensive Entropy
- On ordered weighted averaging aggregation operators in multicriteria decisionmaking
- Proximité et dualité dans un espace hilbertien
- Statistical Inference for Probabilistic Functions of Finite State Markov Chains
- Elicitation of Personal Probabilities and Expectations
- Convexity, Classification, and Risk Bounds
- The complexity of computing the permanent
- I-divergence geometry of probability distributions and minimization problems
- Conditional gradient algorithms with open loop step size rules
- Finding optimum branchings
- Optimum branchings
- Title not available (Why is that?)
- Title not available (Why is that?)
- Sharp uniform convexity and smoothness inequalities for trace norms
- Game theory, maximum entropy, minimum discrepancy and robust Bayesian decision theory
- Title not available (Why is that?)
- The Theory of Max-Min, with Applications
- Convex analysis and nonlinear optimization. Theory and examples
- 10.1162/15324430260185628
- On the consistency of multiclass classification methods
- Finding the nearest point in A polytope
- Large margin methods for structured and interdependent output variables
- Convex analysis and monotone operator theory in Hilbert spaces
- Fast projection onto the simplex and the \(l_1\) ball
- The generalized simplex method for minimizing a linear form under linear inequality restraints
- Composite binary losses
- Smoothing and first order methods: a unified framework
- Uncertainty, Information, and Sequential Experiments
- Accelerated proximal stochastic dual coordinate ascent for regularized loss minimization
- An O(n) algorithm for quadratic knapsack problems
- Learning permutations with exponential weights
- Online linear optimization over permutations
- Online prediction under submodular constraints
- Bandit online optimization over the permutahedron
- Pseudo-Convex Functions
- On surrogate loss functions and \(f\)-divergences
- Nonextensive information theoretic kernels on measures
- Randomized online PCA algorithms with regret bounds that are logarithmic in the dimension
- Value regularization and Fenchel duality
- Information, divergence and risk for binary experiments
- Information geometry and its applications
- Natural language processing (almost) from scratch
- Online learning of Nash equilibria in congestion games
- Regularized optimal transport and the rot mover's distance
- Composite multiclass losses
- On the equivalence of weak learnability and linear separability: new relaxations and efficient boosting algorithms
- Multiclass classification, information, divergence and surrogate risk
- Learning using privileged information: SVM+ and weighted SVM
Cited In (7)
- Variational representations of annealing paths: Bregman information under monotonic embedding
- Tutorial on Amortized Optimization
- Structured learning based heuristics to solve the single machine scheduling problem with release times and sum of completion times
- Cross-entropy loss for recommending efficient fold-over technique
- An investigation for loss functions widely used in machine learning
- Learned-loss boosting
- PyEPO: a PyTorch-based end-to-end predict-then-optimize library for linear and integer programming
Uses Software
This page was built for publication:
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4969074)