Giulia DeSalvo

Learn More
Performance of machine learning algorithms depends critically on identifying a good set of hyperparameters. While current methods offer efficiencies by adaptively choosing new configurations to train, an alternative strategy is to adaptively allocate resources across the selected configurations. We formulate hyperparameter optimization as a pure-exploration(More)
Performance of machine learning algorithms depends critically on identifying a good set of hyperparameters. While recent approaches use Bayesian Optimization to adaptively select configurations, we focus on speeding up random search through adaptive resource allocation. We present HYPERBAND, a novel algorithm for hyperparameter optimization that is simple,(More)
We introduce a novel framework for classification with a rejection option that consists of simultaneously learning two functions: a classifier along with a rejection function. We present a full theoretical analysis of this framework including new data-dependent learning bounds in terms of the Rademacher complexities of the classifier and rejection families(More)
We introduce a broad learning model formed by cascades of predictors, Deep Cascades, that is structured as general decision trees in which leaf predictors or node questions may be members of rich function families. We present new detailed data-dependent theoretical guarantees for learning with Deep Cascades with complex leaf predictors or node question in(More)
We present a new boosting algorithm for the key scenario of binary classification with abstention where the algorithm can abstain from predicting the label of a point, at the price of a fixed cost. At each round, our algorithm selects a pair of functions, a base predictor and a base abstention function. We define convex upper bounds for the natural loss(More)
We introduce a broad family of decision trees, Composite Trees, whose leaf classifiers are selected out of a hypothesis set composed of p subfamilies with different complexities. We prove new data-dependent learning guarantees for this family in the multi-class setting. These learning bounds provide a quantitative guidance for the choice of the hypotheses(More)
The multi-armed bandit problem where the rewards are realizations of general non-stationary stochastic processes is a challenging setting which has not been previously tackled in the bandit literature in its full generality. We present the first theoretical analysis of this problem by deriving guarantees for both the path-dependent dynamic pseudo-regret and(More)
This paper shows a novel method to precisely measure the laser power using an optomechanical system. By measuring a mirror displacement caused by the reflection of an amplitude modulated laser beam, the number of photons in the incident continuous-wave laser can be precisely measured. We have demonstrated this principle by means of a prototype experiment(More)
  • 1