שמיעה = עפ"י רישום שם מלא + מספר ת.ז.  בצ'אט

Join Zoom Meeting
https://zoom.us/j/92610353303

Speaker: Guy Tevet

M.Sc. student under the supervision of Prof. Jonathan Berant

Wednesday, May 20^th, 2020 at 15:00

Evaluating the Evaluation of Diversity in Natural Language Generation

Abstract

Despite growing interest in natural language generation (NLG) models that produce diverse outputs, there is currently no principled method for evaluating the diversity of an NLG system. In this work, we propose a framework for evaluating diversity metrics. The framework measures the correlation between a proposed diversity metric and a diversity parameter, a single parameter that controls some aspect of diversity in generated text. For example, a diversity parameter might be a binary variable used to instruct crowdsourcing workers to generate text with either low or high content diversity. We demonstrate the utility of our framework by: (a) establishing best practices for eliciting diversity judgments from humans, (b) showing that humans substantially outperform automatic metrics in estimating content diversity, and (c) demonstrating that existing methods for controlling diversity by tuning a "decoding parameter" mostly affect form but not meaning. Our framework can advance the understanding of different diversity metrics, an essential step on the road towards better NLG systems.

+ מספר ת.ז.  בצ'אט

Join Zoom Meeting

https://zoom.us/j/94007495169
Meeting ID: 940 0749 5169

Speaker: Assaf Dauber

M.Sc. student under the supervision of Prof. Meir Feder

Wednesday, May 13^th, 2020 at 15:00

Can Implicit Bias Explain Generalization?

Abstract

The notion of implicit bias, or implicit regularization, has been suggested as a means to explain the surprising generalization ability of modern-days overparameterized learning algorithms. This notion refers to the tendency of the optimization algorithm towards a certain structured solution that often generalizes well. Recently, several papers have studied implicit regularization and were able to identify this phenomenon in various scenarios.

In this seminar, we revisit this paradigm in arguably the simplest non-trivial setup, and study the implicit bias of Stochastic Gradient Descent (SGD) in the context of Stochastic Convex Optimization. As a first step, we provide a simple construction that rules out the existence of a  distribution-independent implicit regularizer that governs the generalization ability of SGD.

We then demonstrate a learning problem that rules out a very general class of distribution-dependent implicit regularizers from explaining generalization, which includes strongly convex regularizers as well as non-degenerate norm-based regularizations. Certain aspects of our constructions point out to significant difficulties in providing a comprehensive explanation of an algorithm's generalization performance by solely arguing about its implicit regularization properties.