Bandit Convex Optimization (BCO) is a fundamental framework for decision making under uncertainty, which generalizes many problems from the realm of online and statistical learning. While the special case of linear cost functions is well understood, a gap on the attainable regret for BCO with nonlinear losses remains an important open question. In this paper we take a step towards understanding the best attainable regret bounds for BCO: we give an efficient and near-optimal regret algorithm for BCO with strongly-convex and smooth loss functions. In contrast to previous works on BCO that use time invariant exploration schemes, our method employs an exploration scheme that shrinks with time.

BioSig Technologies, Inc. (NASDAQ: BSGM), a medical technology company commercializing an innovative biomedical signal processing platform designed to improve signal fidelity and uncover the full range of ECG and intra-cardiac signals, today announced that the Company entered into a feasibility study with The Technion Research & Development Foundation Ltd. Based in Haifa, Israel, Technion – Israel Institute of Technology is a public research university offering degrees in science, engineering, and related fields, such as medicine, industrial management, and education. Over the years, the Technion established itself as a leading academic institution in Artificial Intelligence (AI). It is currently ranked as number one in AI in Europe and 15th in the world, with 100 faculty members engaged in areas across the AI spectrum. The feasibility program with BioSig will be led by Asst.

The calculation of curve length is one of the most major components in many modern and classical problem. For example, a handwritten signature involves the computation of the length along the curve (Ooi et al.). When one handles the challenge of length computation in real-life problems he faces several constraints such as additive noise, discretization error, and even partial information. In this work, we address a fundamental question in the field of geometry where we aim to reconstruct a basic property using DNN. The simplest geometric object is a curve, and a simple metric to evaluate a curve is the length.