The promise of learning to learn for robotics rests on the hope that by extracting some information about the learning process itself we can speed up subsequent similar learning tasks. Here, we introduce a computationally efficient online meta-learning algorithm that builds and optimizes a memory model of the optimal learning rate landscape from previously observed gradient behaviors. While per...

This paper is concerned with the question of how to online combine an ensemble of active learners so as to expedite the learning progress during a pool-based active learning session. We develop a powerful active learning master algorithm, based a known competitive algorithm for the multi-armed bandit problem and a novel semi-supervised performance evaluation statistic. Taking an ensemble contai...

We provide insights into the organization and dynamics of recurrent online training algorithms by comparing real time recurrent learning (RTRL) with a new continuous-time online algorithm. The latter is derived in the spirit of a recent approach introduced by Atiya and Parlos [1], which leads to non-gradient search directions. We refer to this approach as Atiya-Parlos learning (APRL) and interp...

Extreme Learning Machine (ELM) is an emerging learning paradigm for nonlinear regression problems and has shown its effectiveness in the machine learning community. An important feature of ELM is that the learning speed is extremely fast thanks to its random projection preprocessing step. This feature is taken advantage of in designing an online parameter estimation algorithm for nonlinear dyna...

In this paper, we study the problem of large-scale Kernel Logistic Regression (KLR). A straightforward approach is to apply stochastic approximation to KLR. We refer to this approach as non-conservative online learning algorithm because it updates the kernel classifier after every received training example, leading to a dense classifier. To improve the sparsity of the KLR classifier, we propose...

Active learning is a machine learning approach to achieving high-accuracy with a small amount of labels by letting the learning algorithm choose instances to be labeled. Most of previous approaches based on discriminative learning use the margin for choosing instances. We present a method for incorporating confidence into the margin by using a newly introduced online learning algorithm and show...

Online learning to rank methods aim to optimize ranking models based on user interactions. The dueling bandit gradient descent (DBGD) algorithm is able to effectively optimize linear ranking models solely from user interactions. We propose an extension of DBGD, called probabilistic multileave gradient descent (PMGD) that builds on probabilistic multileave, a recently proposed highly sensitive a...

In this paper, we consider the contextual variant of MNL-Bandit problem. More specifically, a dynamic set optimization problem, where decision-maker offers subset (assortment) products to consumer and observes response in every round. Consumers purchase maximize their utility. We assume that attributes describe products, mean utility product is linear values these attributes. model choice behav...

The framework of online learning with memory naturally captures learning problems with temporal effects, and was previously studied for the experts setting. In this work we extend the notion of learning with memory to the general Online Convex Optimization (OCO) framework, and present two algorithms that attain low regret. The first algorithm applies to Lipschitz continuous loss functions, obta...