The following pages link to Sham M. Kakade (Q404304):
Displayed 39 items.
- Random design analysis of ridge regression (Q404306) (← links)
- Tail inequalities for sums of random matrices that depend on the intrinsic dimension (Q428742) (← links)
- A spectral algorithm for learning hidden Markov models (Q439990) (← links)
- A tail inequality for quadratic forms of subgaussian random vectors (Q742954) (← links)
- Item:Q404304 (redirect page) (← links)
- Stochastic subgradient method converges on tame functions (Q2291732) (← links)
- A spectral algorithm for latent Dirichlet allocation (Q2345947) (← links)
- Deterministic calibration and Nash equilibrium (Q2462508) (← links)
- When are Overcomplete Topic Models Identifiable? Uniqueness of Tensor Tucker Decompositions with Structured Sparsity (Q2788378) (← links)
- Tensor Decompositions for Learning Latent Variable Models (A Survey for ALT) (Q2835615) (← links)
- (Q2933850) (← links)
- (Q2934062) (← links)
- Tensor decompositions for learning latent variable models (Q2934101) (← links)
- Learning Mixtures of Gaussians in High Dimensions (Q2941572) (← links)
- Learning mixtures of spherical gaussians (Q2986854) (← links)
- (Q3148831) (← links)
- Online Markov Decision Processes (Q3169063) (← links)
- (Q3549654) (← links)
- Playing Games with Approximation Algorithms (Q3575160) (← links)
- Information Consistency of Nonparametric Gaussian Process Methods (Q3604492) (← links)
- (Q4558562) (← links)
- Minimal Realization Problems for Hidden Markov Models (Q4618304) (← links)
- Learning Theory (Q4680883) (← links)
- Learning Theory (Q4680895) (← links)
- Recovering Structured Probability Matrices (Q4993314) (← links)
- (Q4999029) (← links)
- On Nonconvex Optimization for Machine Learning (Q5056442) (← links)
- A Markov Chain Theory Approach to Characterizing the Minimax Optimality of Stochastic Gradient Descent (for Least Squares) (Q5136291) (← links)
- Optimal Dynamic Mechanism Design and the Virtual-Pivot Mechanism (Q5166250) (← links)
- Prediction with a short memory (Q5230363) (← links)
- Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting (Q5271985) (← links)
- Robust Matrix Decomposition With Sparse Corruptions (Q5272229) (← links)
- Stochastic Convex Optimization with Bandit Feedback (Q5300524) (← links)
- (Q5405176) (← links)
- Multi-view Regression Via Canonical Correlation Analysis (Q5432427) (← links)
- Learning Theory (Q5473641) (← links)
- A Short Note on Concentration Inequalities for Random Vectors with SubGaussian Norm (Q6313892) (← links)
- Revisiting the Polyak step size (Q6318065) (← links)
- Model-Based Reinforcement Learning with a Generative Model is Minimax Optimal (Q6320217) (← links)