Search Results for author:
Found 15 papers, 1 papers with code
On the price of exact truthfulness in incentive-compatible online learning with bandit feedback: A regret lower bound for WSU-UX
In this work, our goal is to design an algorithm for the selfish experts problem that is incentive-compatible (IC, or \emph{truthful}), meaning each expert's best strategy is to report truthfully, while also ensuring the algorithm enjoys sublinear regret with respect to the expert with the best belief.
Near-optimal Per-Action Regret Bounds for Sleeping Bandits
In a setting with $K$ total arms and at most $A$ available arms in each round over $T$ rounds, the best known upper bound is $O(K\sqrt{TA\ln{K}})$, obtained indirectly via minimizing internal sleeping regrets.
An improved regret analysis for UCB-N and TS-N
In the setting of stochastic online learning with undirected feedback graphs, Lykouris et al. (2020) previously analyzed the pseudo-regret of the upper confidence bound-based algorithm UCB-N and the Thompson Sampling-based algorithm TS-N.
Adversarial Online Multi-Task Reinforcement Learning
We prove a minimax lower bound of $\Omega(K\sqrt{DSAH})$ on the regret of any learning algorithm and an instance-specific lower bound of $\Omega(\frac{K}{\lambda^2})$ in sample complexity for a class of uniformly-good cluster-then-learn algorithms.
Best-Case Lower Bounds in Online Learning
Much of the work in online learning focuses on the study of sublinear upper bounds on the regret.
Near-Optimal Algorithms for Private Online Learning in a Stochastic Environment
Specifically, for the problem of decision-theoretic online learning with stochastic rewards, we present the first algorithm that achieves an $ O \left( \frac{ \log K}{ \Delta_{\min}} + \frac{\log(K) \min\{\log (\frac{1}{\Delta_{\min}}), \log(T)\}}{\epsilon} \right)$ regret bound, where $\Delta_{\min}$ is the minimum mean reward gap.
A Farewell to Arms: Sequential Reward Maximization on a Budget with a Giving Up Option
We consider a sequential decision-making problem where an agent can take one action at a time and each action has a stochastic temporal extent, i. e., a new action cannot be taken until the previous one is finished.
Dying Experts: Efficient Algorithms with Optimal Regret Bounds
In both cases, we provide matching upper and lower bounds on the ranking regret in the fully adversarial setting.
Multi-Observation Regression
Recent work introduced loss functions which measure the error of a prediction based on multiple simultaneous observations or outcomes.
A Tight Excess Risk Bound via a Unified PAC-Bayesian-Rademacher-Shtarkov-MDL Complexity
Our first main result bounds excess risk in terms of the new complexity.
CompAdaGrad: A Compressed, Complementary, Computationally-Efficient Adaptive Gradient Method
The adaptive gradient online learning method known as AdaGrad has seen widespread use in the machine learning community in stochastic and adversarial online learning problems and more recently in deep learning methods.
Fast rates with high probability in exp-concave statistical learning
We present an algorithm for the statistical learning setting with a bounded exp-concave loss in $d$ dimensions that obtains excess risk $O(d \log(1/\delta)/n)$ with probability at least $1 - \delta$.
Fast Rates for General Unbounded Loss Functions: from ERM to Generalized Bayes
For general loss functions, our bounds rely on two separate conditions: the $v$-GRIP (generalized reversed information projection) conditions, which control the lower tail of the excess loss; and the newly introduced witness condition, which controls the upper tail.
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.
From Stochastic Mixability to Fast Rates
In the non-statistical prediction with expert advice setting, there is an analogous slow and fast rate phenomenon, and it is entirely characterized in terms of the mixability of the loss $\ell$ (there being no role there for $\mathcal{F}$ or $\mathsf{P}$).
