Budgeted Online Influence Maximization
Paper • 2604.19672 • Published
Michal Valko
misovalko
AI & ML interests
large language models, reasoning, fine-tuning, test-time computation, reinforcement learning with human feedback, world models
Recent Activity
authored a paper about 17 hours ago
Budgeted Online Influence Maximization authored a paper about 17 hours ago
Planning in entropy-regularized Markov decision processes and games authored a paper about 17 hours ago
On two ways to use determinantal point processes for Monte Carlo integrationOrganizations
authored 3
papers about 17 hours ago
updated a
dataset about 22 hours ago
authored 2
papers about 23 hours ago
authored 6
papers 1 day ago
Optimal last-iterate convergence in matrix games with bandit feedback using the log-barrier
Paper • 2604.15242 • Published
Best of both worlds: Stochastic & adversarial best-arm identification
Paper • 2604.14860 • Published
Blazing the trails before beating the path: Sample-efficient Monte-Carlo planning
Paper • 2604.14974 • Published
The Harder Path: Last Iterate Convergence for Uncoupled Learning in Zero-Sum Games with Bandit Feedback
Paper • 2604.16087 • Published
Adaptive multi-fidelity optimization with fast learning rates
Paper • 2604.16239 • Published
Sample Complexity Bounds for Stochastic Shortest Path with a Generative Model
Paper • 2604.16111 • Published
authored 3
papers 6 days ago
authored 5
papers 10 days ago
Online Semi-Supervised Learning on Quantized Graphs
Paper • 1203.3522 • Published
Derivative-Free & Order-Robust Optimisation
Paper • 1910.04034 • Published
A simple parameter-free and adaptive approach to optimization under a minimal local smoothness assumption
Paper • 1810.00997 • Published
Gaussian Process Optimization with Adaptive Sketching: Scalable and No Regret
Paper • 1903.05594 • Published
Compressing the Input for CNNs with the First-Order Scattering Transform
Paper • 1809.10200 • Published