no code implementations • ICML 2020 • Corinna Cortes, Giulia Desalvo, Claudio Gentile, Mehryar Mohri, Ningshan Zhang
A general framework for online learning with partial information is one where feedback graphs specify which losses can be observed by the learner.
no code implementations • 24 Jan 2024 • Ke Ye, Heinrich Jiang, Afshin Rostamizadeh, Ayan Chakrabarti, Giulia Desalvo, Jean-François Kagy, Lazaros Karydas, Gui Citovsky, Sanjiv Kumar
In this paper, we present SpacTor, a new training procedure consisting of (1) a hybrid objective combining span corruption (SC) and token replacement detection (RTD), and (2) a two-stage curriculum that optimizes the hybrid objective over the initial $\tau$ iterations, then transitions to standard SC loss.
no code implementations • 28 Sep 2023 • Ke Yu, Stephen Albro, Giulia Desalvo, Suraj Kothawade, Abdullah Rashwan, Sasan Tavakkol, Kayhan Batmanghelich, Xiaoqi Yin
Training high-quality instance segmentation models requires an abundance of labeled images with instance masks and classifications, which is often expensive to procure.
no code implementations • ICCV 2023 • Otilia Stretcu, Edward Vendrow, Kenji Hata, Krishnamurthy Viswanathan, Vittorio Ferrari, Sasan Tavakkol, Wenlei Zhou, Aditya Avinash, Enming Luo, Neil Gordon Alldrin, Mohammadhossein Bateni, Gabriel Berger, Andrew Bunner, Chun-Ta Lu, Javier A Rey, Giulia Desalvo, Ranjay Krishna, Ariel Fuxman
In reaction, we introduce the problem of Agile Modeling: the process of turning any subjective visual concept into a computer vision model through a real-time user-in-the-loop interactions.
no code implementations • 28 Jan 2023 • Gui Citovsky, Giulia Desalvo, Sanjiv Kumar, Srikumar Ramalingam, Afshin Rostamizadeh, Yunjuan Wang
In such a setting, an algorithm can sample examples one at a time but, in order to limit overhead costs, is only able to update its state (i. e. further train model weights) once a large enough batch of examples is selected.
no code implementations • Proceedings of the 25th International Conference on Artificial Intelligence and Statistics 2022 • Zhaobin Kuang, Chidubem Arachie, Bangyong Liang, Pradyumna Narayana, Giulia Desalvo, MICHAEL QUINN, Bert Huang, Geoffrey Downs, Yang Yang
In particular, Firebolt learns the class balance and class-specific accuracy of LFs jointly from unlabeled data.
no code implementations • NeurIPS 2021 • Giulia Desalvo, Claudio Gentile, Tobias Sommer Thune
We derive a novel active learning algorithm in the streaming setting for binary classification tasks.
no code implementations • NeurIPS 2021 • Kareem Amin, Giulia Desalvo, Afshin Rostamizadeh
Consider a setting where we wish to automate an expensive task with a machine learning algorithm using a limited labeling resource.
1 code implementation • NeurIPS 2021 • Gui Citovsky, Giulia Desalvo, Claudio Gentile, Lazaros Karydas, Anand Rajagopalan, Afshin Rostamizadeh, Sanjiv Kumar
The ability to train complex and highly effective models often requires an abundance of training data, which can easily become a bottleneck in cost, time, and computational resources.
no code implementations • ICML 2020 • Corinna Cortes, Giulia Desalvo, Claudio Gentile, Mehryar Mohri, Ningshan Zhang
We present a new active learning algorithm that adaptively partitions the input space into a finite number of regions, and subsequently seeks a distinct predictor for each region, both phases actively requesting labels.
no code implementations • 29 Oct 2017 • Corinna Cortes, Giulia Desalvo, Vitaly Kuznetsov, Mehryar Mohri, Scott Yang
We show that the notion of discrepancy can be used to design very general algorithms and a unified framework for the analysis of multi-armed rested bandit problems with non-stationary rewards.
no code implementations • ICML 2018 • Corinna Cortes, Giulia Desalvo, Claudio Gentile, Mehryar Mohri, Scott Yang
In the stochastic setting, we first point out a bias problem that limits the straightforward extension of algorithms such as UCB-N to time-varying feedback graphs, as needed in this context.
no code implementations • NeurIPS 2016 • Corinna Cortes, Giulia Desalvo, Mehryar Mohri
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.
17 code implementations • 21 Mar 2016 • Lisha Li, Kevin Jamieson, Giulia Desalvo, Afshin Rostamizadeh, Ameet Talwalkar
Performance of machine learning algorithms depends critically on identifying a good set of hyperparameters.