Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/

The convex consistency dimension of a supervised learning task is the lowest prediction dimension $d$ such that there exists a convex surrogate $L: \mathbb{R}^d \times \mathcal Y \to \mathbb R$ that is consistent for the given task. We present a new tool based on property elicitation, $d$-flats, for lower-bounding convex consistency dimension.

We extend the recent framework of Osokin et al.

We consider the problem of fitting a reinforcement learning (RL) model to some given behavioral data under a multi-armed bandit environment. These models have received much attention in recent years for characterizing human and animal decision making behavior. We provide a generic mathematical optimization problem formulation for the fitting problem of a wide range of RL models that appear frequently in scientific research applications, followed by a detailed theoretical analysis of its convexity properties. Based on the theoretical results, we introduce a novel solution method for the fitting problem of RL models based on convex relaxation and optimization. Our method is then evaluated in several simulated bandit environments to compare with some benchmark methods that appear in the literature. Numerical results indicate that our method achieves comparable performance to the state-of-the-art, while significantly reducing computation time. We also provide an open-source Python package for our proposed method to empower researchers to apply it in the analysis of their datasets directly, without prior knowledge of convex optimization.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The authors study the problem of binary classification in the presence of random, class-conditional noise in the training data. They propose two approaches based on a suitable modification of a given surrogate loss function and derive performance bounds. More specifically, they provide guarantees for risk minimization of convex surrogates under random label noise in the general setting, and without any assumptions on the true distribution. Moreover, they provide two alternative approaches for modifying a given surrogate loss function.

We formalize and study the natural approach of designing convex surrogate loss functions via embeddings for problems such as classification or ranking.

Sloan (1988), Cohen (1997), and was most recently highlighted in Avrim Blum's In this work, we focus on learning halfspaces with Massart noise [MN06]: Definition 1.1 A learning algorithm is given i.i.d. The question is whether a polynomial time algorithm exists.