ACDL 2023 Programme Ver1

6th Advanced Course on Data science & machine Learning – ACDL 2023
from Deep Learning to Foundation Models
Riva del Sole Resort & SPA – Castiglione della Pescaia (Grosseto) Tuscany, Italy
10 – 14 June 2023
https://acdl2023.icas.cc/
lod@icas.cc
Schedule Ver. 1.0 (3 pages) – May 31
Sat, 10 June Sun, 11 June Mon, 12 June Tue, 13 June Wed, 14 June
09:00 – 09:50 Yi Ma Zoltan Szabo Panos Pardalos Matej Balog Michal Valko
09:50 – 10:40 Yi Ma Thomas Kipf Tor Lattimore Michal Valko Lucas Beyer
10:40 – 11:20 Coffee break Coffee break Coffee break Coffee break Coffee break
11:20 – 12:10 Yi Ma Thomas Kipf Lucas Beyer Gerhard Paass Gerhard Paass
12:10 – 13:00 Yi Ma Zoltan Szabo Thomas Kipf Matej Balog Lucas Beyer
13:00 – 15:00 Lunch Lunch Lunch Lunch Lunch
15:00 – 15:50 Qing Qu Bruno Loureiro Michal Valko Michal Valko Aakanksha Chowdhery
15:50 – 16:40 Qing Qu Bruno Loureiro Lucas Beyer Gerhard Paass Aakanksha Chowdhery
16:40 – 17:20 Coffee break Coffee break Varun Ojha
17:20 – 18:10 Qing Qu Tor Lattimore Varun Ojha
18:10 – 19:00 Qing Qu Free time Thomas Kipf Free time Free time
19:00 – 19:50 Bruno Loureiro Gerhard Paass

20:00 Dinner Dinner Dinner Dinner Social Dinner
21:00
Participant talks
Conference Room: The Crown (in the conference centre of the Riva del Sole Resort & SPA)
Registration: June 9 @ 18:00 – 19:50 (in the foyer of the conference centre near The Crown conference room)
Inside the Riva del Sole it is mandatory to wear the badge.
Group Photo: June 10 @ 14:40 Meeting point: on the beach!
DIRECTORS:
Giuseppe Nicosia, University of Catania, Italy
Panos Pardalos, University of Florida, USA
LECTURERS:
Matej Balog, DeepMind, London, UK
Lucas Beyer, Google Brain, Zürich, Switzerland
Aakanksha Chowdhery, Google Brain, USA
Thomas Kipf, Google Brain, USA
Tor Lattimore, DeepMind, London, UK
Bruno Loureiro, École Normale Supérieure, France
Yi Ma, University of California, Berkeley, USA
Gerhard Paass, Fraunhofer Institute – IAIS, Germany
Qing Qu, University of Michigan, USA
Zoltan Szabo, LSE, London, UK
Michal Valko, DeepMind Paris & Inria France & ENS MVA
TUTORIAL SPEAKER:
Varun Ojha, Newcastle University, UK
1
ACDL 2023 Lecturers
Matej Balog, DeepMind, London, UK

Lecture 1: “Algorithm Discovery using Reinforcement Learning 1/2”
Lecture 2: “Algorithm Discovery using Reinforcement Learning 2/2”
Lucas Beyer, Google Brain, Zürich, Switzerland

Lecture 1: “Large-Scale Pre-Training & Transfer in Computer Vision and Vision-Text Models 1/2”
Lecture 2: “Large-Scale Pre-Training & Transfer in Computer Vision and Vision-Text Models 2/2”
Lecture 3: “Transformers 1/2”
Lecture 4: “Transformers 2/2”
Aakanksha Chowdhery, Google Brain, USA

Lecture 1: “PaLM-E: An Embodied Language Model”
Lecture 2: “Efficiently Scaling Large Model Inference”
Thomas Kipf, Google Brain, USA

Lecture 1: “Graph Neural Networks 1/2”
Lecture 2: “Graph Neural Networks 2/2”
Lecture 3: “Structured Representation Learning for Perception 1/2”
Lecture 4: “Structured Representation Learning for Perception 2/2”
Tor Lattimore, DeepMind, London, UK

Lecture 1: “Zeroth-order Optimisation: Applications, Algorithms and Analysis, 1/2”
Lecture 2: “Zeroth-order Optimisation: Applications, Algorithms and Analysis, 2/2”
Bruno Loureiro, École Normale Supérieure, France

Lecture 1: “Wonders of high-dimensions: the maths and physics of Machine Learning 1/4”
Yi Ma, University of California, Berkeley, USA

Lecture 1: “An Overview of the Principles of Parsimony and Self-Consistency: The Past, Present, and Future of Intelligence”
Lecture 2: “An Introduction to Low-Dimensional Models and Deep Networks”
Lecture 3: “Parsimony: White-box Deep Networks from Optimizing Rate Reduction”
Lecture 4: “Self-Consistency: Closed-Loop Transcription of Low-Dimensional Structures via Maximin Rate Reduction”
Gerhard Paass, Fraunhofer Institute - IAIS, Germany

Lecture 1: “Introduction to Foundation Models”
Lecture 2: “Foundation Models for Retrieval Applications”
Lecture 3: “Combining Foundation Models with External Text Resources”
Lecture 4: “Approaches to Increase Trustworthiness of Foundation Models”

Lecture : “Diffusion capacity of single and interconnected networks”
Qing Qu, University of Michigan, USA

Lecture 1: “Low-Dimensional and Nonconvex Models for Shallow Representation Learning”
Lecture 2: “Low-Dimensional Structures in Deep Representation Learning I”
Lecture 3: “Low-Dimensional Structures in Deep Representation Learning II”
Lecture 4: “Robust Learning of Overparameterized Networks via Low-Dimensional Models”
Zoltan Szabo, LSE, London, UK

Lecture 1: “Shape-Constrained Kernel Machines and Their Applications”
Lecture 2: “Beyond Mean Embedding: The Power of Cumulants in RKHSs”
Michal Valko, DeepMind Paris & Inria France & ENS MVA
Lecture 1: “Reinforcement learning”
Lecture 2: “Deep Reinforcement Learning”
Lecture 3: “Learning by Bootstrapping: Representation Learning”
Lecture 4: “Learning by Bootstrapping: World Models”
2
ACDL 2023 Tutorial Speaker
Varun Ojha, Newcastle University, UK

Tutorial 1: “Backpropagation Neural Tree”
Tutorial 2: “Sensitivity Analysis of Deep Learning and Optimization Algorithms”
The Accepted Talks

Tue, 13 June @ 21:00
Each talk must compulsorily last no longer than 8 minutes.
Edina Rosta, “Enhanced Sampling Simulations of Biomolecular Systems”

Federico Nocentini, “Speech-Driven 3D Talking Head animation using facial landmarks”
Roberta De Fazio, “Merging Model-Based and Data-Driven Approaches for Resilient Systems Digital Twins Design”
Alberto Baldrati, “Zero-Shot Composed Image Retrieval with Textual Inversion”
Alena van Bommel, “Accurate epigenetic aging clocks using hydroxymethylation data”
Emanuele Vivoli, “MUST-VQA: MUltilingual Scene-text VQA”
Niccolò Biondi, “CoReS: Compatible Representations via Stationarity”
Olivier Caelen, “Are your models well calibrated?”
Andrea Mastropietro, “Leveraging positive-unlabeled learning and graph neural network explainability for disease gene
prioritization”
Igor KoÇakowski, “GLM: General Language Model Pretraining with Autoregressive Blank Infilling”
Oren Neumann, “A universal performance metric for RL”
Federico Motta, “Incremental Data-Preparation Pipeline”
Hamza Amrani, “Deep Embedded Open Vocabulary Electroencephalography-to-Text Decoding using Pre-Trained Large
Language Models”
Nik Schwichtenberg, “Data Driven Welding Optimization”
“Those who have an eye find what they are looking for even with their eyes closed”
“Chi ha occhio trova quel che cerca anche a occhi chiusi”
Italo Calvino.

ACDL 2023 Programme Ver1

Uploaded by

Copyright:

Available Formats

ACDL 2023 Programme Ver1

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

ACDL 2023 Programme Ver1

Uploaded by

Copyright:

Available Formats

6th Advanced Course on Data science & machine Learning – ACDL 2023

from Deep Learning to Foundation Models

Schedule Ver. 1.0 (3 pages) – May 31

19:00 – 19:50 Bruno Loureiro Gerhard Paass

Matej Balog, DeepMind, London, UK

Lucas Beyer, Google Brain, Zürich, Switzerland

Aakanksha Chowdhery, Google Brain, USA

Thomas Kipf, Google Brain, USA

Tor Lattimore, DeepMind, London, UK

Bruno Loureiro, École Normale Supérieure, France

Yi Ma, University of California, Berkeley, USA

Gerhard Paass, Fraunhofer Institute - IAIS, Germany

Panos Pardalos, University of Florida, USA

Qing Qu, University of Michigan, USA

Zoltan Szabo, LSE, London, UK

Varun Ojha, Newcastle University, UK

The Accepted Talks

Each talk must compulsorily last no longer than 8 minutes.

Edina Rosta, “Enhanced Sampling Simulations of Biomolecular Systems”

“Chi ha occhio trova quel che cerca anche a occhi chiusi”

You might also like