Search Results for author:
Found 21 papers, 2 papers with code
Generalization Guarantees via Algorithm-dependent Rademacher Complexity
Algorithm- and data-dependent generalization bounds are required to explain the generalization behavior of modern machine learning algorithms.
The Risks of Recourse in Binary Classification
Algorithmic recourse provides explanations that help users overturn an unfavorable decision by a machine learning system.
Accelerated Rates between Stochastic and Adversarial Online Convex Optimization
In the fully adversarial case our bounds gracefully deteriorate to match the minimax regret.
Modifying Squint for Prediction with Expert Advice in a Changing Environment
Hence, we provide a new algorithm, Squint-CE, which is suitable for a changing environment and preserves the properties of Squint.
Attribution-based Explanations that Provide Recourse Cannot be Robust
Finally, we strengthen our impossibility result for the restricted case where users are only able to change a single attribute of $x$, by providing an exact characterization of the functions $f$ to which impossibility applies.
Between Stochastic and Adversarial Online Convex Optimization: Improved Regret Bounds via Smoothness
case, our bounds match the rates one would expect from results in stochastic acceleration, and in the fully adversarial case they gracefully deteriorate to match the minimax regret.
Scale-free Unconstrained Online Learning for Curved Losses
We follow up on this observation by showing that there is in fact never a price to pay for adaptivity if we specialise to any of the other common supervised online learning losses: our results cover log loss, (linear and non-parametric) logistic regression, square loss prediction, and (linear and non-parametric) least-squares regression.
Robust Online Convex Optimization in the Presence of Outliers
If the outliers are chosen adversarially, we show that a simple filtering strategy on extreme gradients incurs O(k) additive overhead compared to the usual regret bounds, and that this is unimprovable, which means that k needs to be sublinear in the number of rounds.
Distributed Online Learning for Joint Regret with Communication Constraints
Each round, an adversary first activates one of the agents to issue a prediction and provides a corresponding gradient, and then the agents are allowed to send a $b$-bit message to their neighbors in the graph.
MetaGrad: Adaptation using Multiple Learning Rates in Online Learning
We provide a new adaptive method for online convex optimization, MetaGrad, that is robust to general convex losses but achieves faster rates for a broad class of special functions, including exp-concave and strongly convex functions, but also various types of stochastic and non-stochastic functions without any curvature.
Explaining Predictions by Approximating the Local Decision Boundary
We address this by introducing a new benchmark data set with artificially generated Iris images, and showing that we can recover the latent attributes that locally determine the class.
Lipschitz Adaptivity with Multiple Learning Rates in Online Learning
For MetaGrad, we further improve the computational efficiency of handling constraints on the domain of prediction, and we remove the need to specify the number of rounds in advance.
The Many Faces of Exponential Weights in Online Learning
A standard introduction to online learning might place Online Gradient Descent at its center and then proceed to develop generalizations and extensions like Online Mirror Descent and second-order methods.
Combining Adversarial Guarantees and Stochastic Fast Rates in Online Learning
We consider online learning algorithms that guarantee worst-case regret rates in adversarial environments (so they can be deployed safely and will perform robustly), yet adapt optimally to favorable stochastic environments (so they will perform well in a variety of settings of practical importance).
MetaGrad: Multiple Learning Rates in Online Learning
In online convex optimization it is well known that certain subclasses of objective functions are much easier than arbitrary convex functions.
Fast rates in statistical and online learning
For bounded losses, we show how the central condition enables a direct proof of fast rates and we prove its equivalence to the Bernstein condition, itself a generalization of the Tsybakov margin condition, both of which have played a central role in obtaining fast rates in statistical learning.
Second-order Quantile Methods for Experts and Combinatorial Games
We aim to design strategies for sequential decision making that adjust to the difficulty of the learning problem.
Learning the Learning Rate for Prediction with Expert Advice
Most standard algorithms for prediction with expert advice depend on a parameter called the learning rate.
PAC-Bayes Mini-tutorial: A Continuous Union Bound
When I first encountered PAC-Bayesian concentration inequalities they seemed to me to be rather disconnected from good old-fashioned results like Hoeffding's and Bernstein's inequalities.
A Second-order Bound with Excess Losses
We study online aggregation of the predictions of experts, and first show new second-order regret bounds in the standard setting, which are obtained via a version of the Prod algorithm (and also a version of the polynomially weighted average algorithm) with multiple learning rates.
Rényi Divergence and Kullback-Leibler Divergence
R\'enyi divergence is related to R\'enyi entropy much like Kullback-Leibler divergence is related to Shannon's entropy, and comes up in many settings.
