Search Results for author:
Found 14 papers, 1 papers with code
Learning SMaLL Predictors
We present a new machine learning technique for training small resource-constrained predictors.
Online Learning with a Hint
We show that the player can benefit from such a hint if the set of feasible actions is sufficiently round.
Adaptive Neural Networks for Efficient Inference
We first pose an adaptive network evaluation scheme, where we learn a system to adaptively choose the components of a deep network to be evaluated for each example.
Linear Learning with Sparse Data
Linear predictors are especially useful when the data is high-dimensional and sparse.
Bandit Smooth Convex Optimization: Improving the Bias-Variance Tradeoff
The best algorithm for the general bandit convex optimization problem guarantees a regret of $\widetilde{O}(T^{5/6})$, while the best known lower bound is $\Omega(T^{1/2})$.
Online Learning with Feedback Graphs: Beyond Bandits
We study a general class of online learning problems where the feedback is specified by a graph.
Bandit Convex Optimization: sqrt{T} Regret in One Dimension
We analyze the minimax regret of the adversarial bandit convex optimization problem.
The Blinded Bandit: Learning with Adaptive Feedback
We study an online learning setting where the player is temporarily deprived of feedback each time it switches to a different action.
Online Learning with Composite Loss Functions
This class includes problems where the algorithm's loss is the minimum over the recent adversarial values, the maximum over the recent values, or a linear combination of the recent values.
Online Learning with Costly Features and Labels
In particular, we show that with switching costs, the attainable rate with bandit feedback is $T^{2/3}$.
Bandits with Switching Costs: T^{2/3} Regret
We prove that the player's $T$-round minimax regret in this setting is $\widetilde{\Theta}(T^{2/3})$, thereby closing a fundamental gap in our understanding of learning with bandit feedback.
Online Learning with Switching Costs and Other Adaptive Adversaries
In particular, we show that with switching costs, the attainable rate with bandit feedback is $\widetilde{\Theta}(T^{2/3})$.
Distribution-Calibrated Hierarchical Classification
While many advances have already been made on the topic of hierarchical classi- fication learning, we take a step back and examine how a hierarchical classifica- tion problem should be formally defined.
From Online to Batch Learning with Cutoff-Averaging
We present cutoff averaging", a technique for converting any conservative online learning algorithm into a batch learning algorithm.
