A Short Note on Concentration Inequalities for Random Vectors with SubGaussian Norm
arXiv:1902.03736
Abstract
In this note, we derive concentration inequalities for random vectors with subGaussian norm (a generalization of both subGaussian random vectors and norm bounded random vectors), which are tight up to logarithmic factors.
Cited by in corpus (26)
- On the Convergence of Adaptive Gradient Methods for Nonconvex Optimization
- On Nonconvex Optimization for Machine Learning: Gradients, Stochasticity, and Saddle Points
- Meta Dynamic Pricing: Transfer Learning Across Experiments
- Some Theoretical Insights into Wasserstein GANs
- Minibatch optimal transport distances; analysis and applications
- A High Probability Analysis of Adaptive SGD with Momentum
- Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping
- Robust Policy Gradient against Strong Data Corruption
- On Primal-Dual Approach for Distributed Stochastic Convex Optimization over Networks
- Distributionally Robust Graph Learning from Smooth Signals under Moment Uncertainty
- On Thompson Sampling with Langevin Algorithms
- A Simple Reward-free Approach to Constrained Reinforcement Learning
- Follow the Perturbed Leader: Optimism and Fast Parallel Algorithms for Smooth Minimax Games
- Optimizing Black-box Metrics with Adaptive Surrogates
- Online DR-Submodular Maximization with Stochastic Cumulative Constraints
- A Free Lunch from the Noise: Provable and Practical Exploration for Representation Learning
- Adapting to Function Difficulty and Growth Conditions in Private Optimization
- Improved Regret Bound and Experience Replay in Regularized Policy Iteration
- Improved Regret Bounds for Online Submodular Maximization
- Learning with User-Level Privacy
- Stochastic Optimization under Distributional Drift
- Locally Private k-Means in One Round
- Numerical methods for the resource allocation problem in networks
- Vector Optimization with Stochastic Bandit Feedback
- Second-Order Convergence of Asynchronous Parallel Stochastic Gradient Descent: When Is the Linear Speedup Achieved?
- Neural Estimation of Statistical Divergences