#### Filter Results:

- Full text PDF available (8)

#### Publication Year

2014

2017

- This year (3)
- Last 5 years (9)
- Last 10 years (9)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Key Phrases

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)

- Corinna Cortes, Giulia DeSalvo, Mehryar Mohri
- ALT
- 2016

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)

- Giulia DeSalvo, Mehryar Mohri, Umar Syed
- ALT
- 2015

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)

- Corinna Cortes, Giulia DeSalvo, Mehryar Mohri
- NIPS
- 2016

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)

- Corinna Cortes, Giulia DeSalvo, Mehryar Mohri, Scott Yang
- ArXiv
- 2017

We introduce and analyze an on-line learning setting where the learner has the added option of abstaining from making a prediction at the price of a fixed cost. When the learner abstains, no feedback is provided, and she does not receive the label associated with the example. We design several algorithms and derive regret guarantees in both the adversarial… (More)

- Giulia DeSalvo, Mehryar Mohri
- AAAI
- 2016

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)

- Corinna Cortes, Giulia DeSalvo, Vitaly Kuznetsov, Mehryar Mohri, Scott Yang
- ArXiv
- 2017

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)

- Kazuhiro Agatsuma, Daniel Friedrich, +4 authors Seiji Kawamura
- Optics express
- 2014

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
- ›