TALK KEYWORD INDEX

This page contains an index consisting of author-provided keywords.

A | |

accelerated gradient descent | |

Accelerated Methods | |

Accelerated Stochastic Gradient Descent | |

Acceleration | |

active learning | |

Adaptive data analysis | |

adaptive methods | |

adaptive regret bounds | |

adaptivity | |

adversarial and stochastic rewards | |

Adversarial Multi-armed bandits | |

agnostic learning | |

algorithm estimation | |

Algorithm-dependent Generalization Error Bounds | |

Algorithmic stability | |

analysis of heuristics | |

approximate message-passing algorithm | |

approximation | |

approximation algorithms | |

approximation rate | |

assignment problem | |

Attribute Efficient | |

Autoregressive processes | |

average-case complexity | |

B | |

Banach space | |

Bandit convex optimization | |

bandit feedback | |

bandit linear optimization | |

Bandits | |

bandits with infinitely many arms | |

Bayesian inference | |

Bayesian regret | |

best-arm identification | |

bias | |

Big data | |

Binary classification | |

bisection algorithm | |

boosting | |

Burer Monteiro | |

C | |

chaining | |

Cohort Analysis | |

communication constraints | |

Complexity Theory | |

Composite losses | |

compressed sensing | |

Computational Complexity | |

Computational methods | |

concentration inequalities | |

Conformal inference | |

contextual bandits | |

convergence | |

Convergence Rate | |

Convex optimization | |

convexity | |

crowd-labeling | |

cumulative regret | |

cutting plane methods | |

D | |

data visualization | |

Deep Learning | |

deep priors | |

Delayed feedback | |

Deletion channel | |

density estimation | |

dependent data | |

detecting correlations | |

Detection | |

Differential privacy | |

dimension reduction | |

Direct Sum | |

distance estimation | |

distance sketches | |

Distributed estimation | |

Distribution Estimation | |

dynamic regret | |

E | |

Efficient | |

Empirical process theory | |

empirical risk minimization | |

entropic penalization | |

entropy | |

Erdos Renyi Model | |

exponential weights | |

F | |

fairness | |

Fano's inequality | |

fast rates | |

feedback graphs | |

Finite Sample Analysis | |

finite sample bounds | |

first-order methods | |

Fokker--Planck | |

Frank-Wolfe | |

Free energy | |

free probability | |

Functional Estimation | |

G | |

Gaussian | |

Generalization | |

Generalization theory | |

generalized linear model | |

generative models | |

geodesically convex optimization | |

Gibbs distribution | |

gradient descent | |

gradient flow | |

Gradient oracle | |

Gradient Temporal Difference | |

graph homomorphism numbers | |

graph sampling | |

greedy algorithm | |

groups | |

H | |

Halfspaces | |

Hausdorff distance | |

heat equation | |

Heteroscedastic Noise | |

High Dimensional Statistics | |

High-dimensional geometry | |

high-dimensional inference | |

High-dimensional Statistics | |

high-dimensionality | |

Higher-Order Optimization | |

histogram learning | |

Horvitz-Thompson estimator | |

hypothesis testing | |

I | |

Implicit regularization | |

importance sampling | |

Incentivizing Exploration | |

increasing learning rate | |

independent component analysis | |

Information Directed Sampling | |

Information Theory | |

integer programming | |

Ising Model | |

Ising models | |

K | |

k-PCA | |

kernel methods | |

Kullback-Leibler divergence | |

L | |

L1 regression | |

Langevin algorithm | |

Langevin Diffusion | |

Langevin dynamics | |

Langevin Monte Carlo | |

Lasso | |

learning | |

Learning theory | |

least squares | |

Least Squares Regression | |

Lewis weights | |

likelihood ratio fluctuations | |

Linear dynamical systems | |

Lipschitz continuity | |

local minima | |

log-concave | |

low rank | |

Lower bounds | |

M | |

Manifold Learning | |

Margin condition | |

Markov chain Monte Carlo | |

Markov decision processes | |

Markov random fields | |

martingales | |

Matrix Completion | |

Matrix factorization | |

maximum likelihood estimation | |

MCMC | |

Mean-field approximation | |

Membership oracle | |

memory constraints | |

Memory-bounded learning | |

metastability | |

metric compression | |

Metropolis-adjusted Langevin algorithm | |

Minimax lower bound | |

minimax lower bounds | |

minimax rates | |

Minimax Risk | |

Minimaxity | |

Mixtures of Gaussians | |

Mixtures of Linear Regressions | |

moments | |

multi-armed bandit | |

multi-armed bandits | |

Multi-index models | |

multiscale scan statistics | |

mutual information | |

N | |

nasty noise | |

nearest neighbor | |

Nearest-neighbors | |

Nesterov's accelerated gradient method | |

Network Data | |

network motifs | |

neural network | |

Neural networks | |

Newton's method | |

Noise addition | |

non-convex | |

Non-convex Learning | |

non-convex optimization | |

non-Gaussian component analysis | |

non-stationary environments | |

non-stochastic bandits | |

nonconvex | |

Nonconvex optimization | |

nonlinear optimization | |

Nonparametric classification | |

Nonstochastic bandits | |

O | |

On-line learning | |

online algorithms | |

Online Combinatorial Optimization | |

Online Convex Optimization | |

Online learning | |

Online Linear Optimization | |

operator splitting | |

optimal transport | |

optimistic online mirror descent | |

optimization | |

Ornstein-Uhlenbeck | |

outlier-robust learning | |

Over-parameterized models | |

P | |

PAC Learning | |

PAC-Bayes Theory | |

pairwise comparisons | |

Parameter-free | |

Parameterized family of MDPs | |

partition function | |

perceptron | |

permutation and randomization | |

permutation-based models | |

phase retrieval | |

phase transition | |

phase transitions | |

planning | |

planted clique | |

Polynomial Threshold Functions | |

Positive-definite kernels | |

Prediction from Experts | |

prediction with expert advice | |

principal component analysis | |

privacy | |

probability | |

projection | |

Property testing | |

proximal operators | |

Q | |

quantization | |

R | |

Rademacher Complexity | |

random walk | |

Randomized algorithms | |

ranking | |

Reach | |

Reductions | |

regression | |

Regret | |

regularization | |

reinforcement learning | |

ReLU activation | |

replica symmetry | |

representation learning | |

Restricted Eigenvalue | |

Riemannian Manifold | |

Riemannian optimization | |

risk | |

Robust Learning | |

S | |

saddle points | |

Sample complexity | |

sampling | |

SDP | |

second moment method | |

Second-Order Optimization | |

semi-bandit | |

Semi-parametric models | |

Semi-Random Model | |

Semi-Verified Learning | |

semidefinite | |

semidefinite programming | |

sequential learning | |

SGD | |

shape-constrained estimation | |

simple regret | |

Simulated annealing | |

Single-index models | |

Sinkhorn algorithm | |

small-loss regret bounds | |

smoothed analysis | |

smoothness | |

Social Learning | |

Sparse | |

Sparse Linear Regression | |

spectral analysis | |

Spectral initialization | |

Spiked random matrix models | |

spin glasses | |

Stability of Learning Algorithms | |

Stable Rank | |

stationarity tests | |

stationary point | |

statistical learning | |

statistical learning theory | |

Statistical queries | |

statistical-computational gap | |

Statistics | |

Stochastic Algorithms | |

Stochastic Approximation | |

Stochastic Differential Equations | |

Stochastic Gradient Descent | |

Stochastic Gradient Langevin Dynamics | |

Stochastic Gradient Method | |

Strong data processing inequality | |

Sub-Gaussian Mixture Models | |

submodular optimization | |

sum-of-squares | |

Switching Budgets | |

Switching costs | |

System identification | |

T | |

t-SNE | |

Temporal Difference | |

temporal difference learning | |

the cavity method | |

Tikhonov regularization | |

Time series | |

Trace reconstruction | |

Transfer learning | |

Two Timescale | |

U | |

UCB | |

unreliable data set | |

unsupervised learning | |

Upper Confidence Bound | |

V | |

variance reduction | |

Variational methods | |

VC Dimension | |

verification | |

W | |

Wasserstein Distance | |

Wasserstein gradient flow | |

Wasserstein metric | |

Z | |

zero-sum games |