Search Results for author:
Found 13 papers, 2 papers with code
AdaNet: A Scalable and Flexible Framework for Automatically Learning Ensembles
AdaNet is a lightweight TensorFlow-based (Abadi et al., 2015) framework for automatically learning high-quality ensembles with minimal expert intervention.
Efficient Gradient Computation for Structured Output Learning with Rational and Tropical Losses
In this paper, we design efficient gradient computation algorithms for two broad families of structured prediction loss functions: rational and tropical losses.
Foundations of Sequence-to-Sequence Modeling for Time Series
The availability of large amounts of time series data, paired with the performance of deep-learning algorithms on a broad class of problems, has recently led to significant interest in the use of sequence-to-sequence models for time series forecasting.
Online Non-Additive Path Learning under Full and Partial Information
We study the problem of online path learning with non-additive gains, which is a central problem appearing in several applications, including ensemble structured prediction.
Theory and Algorithms for Forecasting Time Series
We present data-dependent learning bounds for the general scenario of non-stationary non-mixing stochastic processes.
Discriminative State Space Models
In this paper, we introduce and analyze Discriminative State-Space Models for forecasting non-stationary time series.
Discrepancy-Based Algorithms for Non-Stationary Rested Bandits
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.
AdaNet: Adaptive Structural Learning of Artificial Neural Networks
We present new algorithms for adaptively learning artificial neural networks.
Structured Prediction Theory Based on Factor Graph Complexity
We give new data-dependent margin guarantees for structured prediction for a very wide family of loss functions and a general family of hypotheses, with an arbitrary factor graph decomposition.
Learning Theory and Algorithms for Forecasting Non-stationary Time Series
We present data-dependent learning bounds for the general scenario of non-stationary non-mixing stochastic processes.
Voted Kernel Regularization
This paper presents an algorithm, Voted Kernel Regularization , that provides the flexibility of using potentially very complex kernel functions such as predictors based on much higher-degree polynomial kernels, while benefitting from strong learning guarantees.
Multi-Class Deep Boosting
We give new data-dependent learning bounds for convex ensembles in the multi-class classification setting expressed in terms of the Rademacher complexities of the sub-families composing the base classifier set, and the mixture weight assigned to each sub-family.
