Competition-Level Code Generation with AlphaCode

-------------------------------------------------------------------
                Joint Seminar
Department of Computer Science and Engineering, HKUST
                    and
Data Science and Analytics (DSA) Thrust
Information Hub, HKUST(GZ)
------------------------------------------------------------------

Speaker: Dr. Junyoung CHUNG
         Research Scientist
         DeepMind

Title: "Competition-Level Code Generation with AlphaCode"

Date:   Monday, 7 March 2022

Time:   4:00pm - 5:00pm (Hong Kong Local Time)

Zoom link:
https://hkust.zoom.us/j/928308079?pwd=MW9wTCtlSDd2MnViZGdNd2oreUpXZz09

Meeting ID:     928 308 079
Passcode:       20212022


Abstract:

Programming is a ubiquitous problem-solving tool. Developing AI systems
that can independently generate programs or assist programmers can change
the paradigm of programming. Recent large-scale language models have
demonstrated an impressive ability to generate code, and they are now able
to complete simple programming tasks.

However, these models are rather weak when evaluated on more complex,
unseen problems that require problem-solving skills beyond simply
translating instructions into code. For example, competitive programming
problems which require an understanding of algorithms and complex natural
language remain extremely challenging. To address this gap, we introduce
AlphaCode, a system for code generation that can create novel solutions to
these problems that require deeper reasoning. In simulated evaluations on
recent programming competitions on the Codeforces platform, AlphaCode
achieved on average a ranking of the top 54.3% in competitions with more
than 5,000 participants. Today, I will present the key ideas introduced in
AlphaCode and insights for tackling competitive programming.


*************
Biography:

Junyoung Chung is a research scientist at DeepMind. He received his PhD
degree from the University of Montreal / MILA under the supervision of
Professor Yoshua Bengio. He has contributed as a core researcher in
AlphaStar and AlphaCode projects at DeepMind. His research interests
include various deep learning ideas, multimodal learning, natural language
processing and program synthesis.