The AutoML Podcast
Episodes
MLGym: A New Framework and Benchmark for Advancing AI Research Agents
31 Oct 2025
Contributed by Lukas
AutoML is dead an LLMs have killed it? MLGym is a benchmark and framework testing this theory. Roberta Raileanu and Deepak Nathani discuss how well cu...
Leverage Foundational Models for Black-Box Optimization
22 Sep 2025
Contributed by Lukas
Where and how can we use foundation models in AutoML? Richard Song, researcher at Google DeepMind, has some answers. Starting off from his position pa...
Nyckel - Building an AutoML Startup
07 Mar 2025
Contributed by Lukas
Oscar Beijbom is talking about what it's like to run an AutoML startup: Nyckel. Beyond that, we chat about the differences between academia and i...
Neural Architecture Search: Insights from 1000 Papers
03 Dec 2024
Contributed by Lukas
Colin White, head of research at Abacus AI, takes us on a tour of Neural Architecture Search: its origins, important paradigms and the future of NAS i...
Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How
08 Aug 2024
Contributed by Lukas
There are so many great foundation models in many different domains - but how do you choose one for your specific problem? And how can you best finetu...
Discovering Temporally-Aware Reinforcement Learning Algorithms
24 Jun 2024
Contributed by Lukas
Designing algorithms by hand is hard, so Chris Lu and Matthew Jackson talk about how to meta-learn them for reinforcement learning. Many of the conc...
X Hacking: The Threat of Misguided AutoML
27 May 2024
Contributed by Lukas
AutoML can be a tool for good, but there are pitfalls along the way. Rahul Sharma and David Selby tell us about how AutoML systems can be used to give...
Introduction To New Co-Host, Theresa Eimer
27 May 2024
Contributed by Lukas
In today's episode, we're introducing the very special Theresa Eimer to the show. Theresa will be taking over the hosting of many of the fut...
AutoGluon: The Story
05 Sep 2023
Contributed by Lukas
Today we're talking with Nick Erickson from AutoGluon.We discuss AutoGluon's fascinating origin story, its unique point of view, the science...
How to Integrate Logic and Argumentation into Human-Centric AutoML
26 Jun 2023
Contributed by Lukas
Today we're talking with Joseph Giovanelli about his work on integrating logic and argumentation into AutoML systems.Joseph is a PhD student at t...
How to Design an AutoML System using Error Decomposition
04 Jun 2023
Contributed by Lukas
Today we're talking with Caitlin Owen, a post-doc at the University of Otago about her work on error decomposition.She recently published a paper...
The Semantic Layer and AutoML
16 May 2023
Contributed by Lukas
Today we're talking with Gaurav Rao, the EVP & GM of Machine Learning and AI at AtScale, a company centered around the semantic layer.For som...
Foundation Models: The term and its origins
29 Apr 2023
Contributed by Lukas
Today Ankush Garg is speaking with Rishi Bommasani, PhD student at Stanford and one of the originator of the term Foundation Models.They’re talking ...
The Business and Engineering of AutoML Products with Raymond Peck
06 Apr 2023
Contributed by Lukas
Today we're talking with Raymond Peck, a senior engineer and director in the AutoML space. He spent time at H2O, dotData, Alteryx and many other ...
TabPFN: A Revolution in AutoML?
02 Mar 2023
Contributed by Lukas
Today we’re talking to Noah Hollmann and Samuel Muller about their paper on TabPFN - which is an incredible spin on AutoML based on Bayesian inferen...
How financial institutions manage model risk
07 Feb 2023
Contributed by Lukas
Today we’re talking to Sean Sexton, the Director of Modeling and Analytics Consulting at KPMG, about the role of models in financial institutions an...
How to solve dynamical systems by fusing data and mechanism
12 Jan 2023
Contributed by Lukas
Today we’re talking to Matt Levine. Matt is a PhD student in computing and mathematical sciences at Caltech, and he focuses on improving the predict...
DASH: How to Search Over Convolutions
20 Dec 2022
Contributed by Lukas
Today we’re chatting with Junhong Shen, a PhD student at Carnegie Mellon.Junhong and her team are working on the generalizability of NAS algorithms ...
Human-Centered AutoML: The New Paradigm
03 Dec 2022
Contributed by Lukas
Today we're speaking with Marius Lindauer and it is certainly one of my favorite episodes!As you’ll hear, Marius is full of ideas for where Aut...
BERT-Sort: How to use language models to semantically order categorical values
24 Nov 2022
Contributed by Lukas
Today Ankush Garg is talking to Mehdi Bahrami about his recent project: BERT-Sort.BERT-Sort is an example of how large language models can add useful ...
SAT: The Peculiar Origins of AutoML
11 Nov 2022
Contributed by Lukas
In today's episode, we’re talking to Lars Kothoff about the fascinating origin story of AutoML (as he sees it), and how it emerged from the SAT...
How to use evolutionary strategies for online AutoML
17 Oct 2022
Contributed by Lukas
Today we’re talking to Cedric Kulbach about online learning, the challenges of doing it properly, why it is so promising, how it’s connected to ev...
A Narration of The Bitter Lesson
26 Sep 2022
Contributed by Lukas
This short episode is a narration of Richard Sutton's The Bitter Lesson.Richard Sutton is a distinguished research scientist at DeepMind and a pr...
Examining Tabular Deep Learning
19 Sep 2022
Contributed by Lukas
More drama in the contest between traditional machine learning models and deep learning models when it comes to tabular data.We have on the show Vadim...
The Paths to AGI
05 Sep 2022
Contributed by Lukas
Today we’re speaking with Jeff Clune about a new path towards general artificial intelligence, that he calls AI Generating Algorithms (AI-GAs).Jeff ...
How to evaluate a metalearning system
29 Aug 2022
Contributed by Lukas
Today I'm speaking with Jan N. van Rijn about metalearning.Jan is an assistant professor at Leiden University, where he also did his PhD. He is o...
Active Dendrites: Brain-inspired multi-task learning
23 Aug 2022
Contributed by Lukas
Today we’re speaking with three researchers: Karan Grewal, Abhi Iyer and Akash Velu, about multi-task learning and how their new brain-inspired appr...
Smart NAS via Co-Regulated Shaping Reinforcement
08 Aug 2022
Contributed by Lukas
Today I’m speaking with Mayukh Das about using neural architecture search for resource-constrained devices and about a new multi-objective reinforce...
The measures of intelligence
25 Jul 2022
Contributed by Lukas
Today we’re speaking with José Hernández-Orallo. José is a Professor at the Polytechnic University of València in Spain and a Senior Research Fe...
Upgrading human evaluators with assessor models
24 Jul 2022
Contributed by Lukas
Today I’m talking with Wout Schellaert about assessor models. Wout is a PhD student at the Polytechnic University of Valencia..We’ll be covering a...
How to explain using analogies
24 Jul 2022
Contributed by Lukas
Today we’re talking to Karthi Ramamurthy about a novel approach to similarity learning explainability.Karthi is a research staff member in IBM Resea...
How is NAS going to evolve?
24 Jul 2022
Contributed by Lukas
Today I’m speaking with Vasco Lopes, about the state of Neural Architecture Search, NAS, and about a new method that he published that takes a very ...
How deep learning can be used for tabular datasets
23 Jul 2022
Contributed by Lukas
Today I’m speaking with Yury Gorishniy about the state of the competition between Deep Learning and Gradient Boosted Decision Trees when it comes to...
When is missing data not a problem?
23 Jul 2022
Contributed by Lukas
Today we’ll be speaking with Julian Morimoto about missing data, its impact on the reliability of statistical inference, and two theorems that he re...
Why this show
23 Jul 2022
Contributed by Lukas
In this episode, Adam introduces the show, the motivations for it, and why and how you should participate.
Are your experiments reproducible?
23 Jul 2022
Contributed by Lukas
Today we're speaking with Luigi Quaranta about the state of reproducibility in machine learning.Luigi published a taxonomy of support for reprodu...
Manipulating Your Reputation
30 May 2022
Contributed by Lukas
In this episode, Adam speaks with Doctor Torsten Ensslin about simulating reputation networks and their manipulation using Information Theory.Torsten ...
Multi-Objective AutoML
23 May 2022
Contributed by Lukas
In this episode, Adam discusses Multi-objective optimization with Laurent Parmentier.Laurent works at OVHCloud, most recently as a data scientist but ...
ML Interpretability with Jessica Schrouff
16 May 2022
Contributed by Lukas
This episode launches us into the deep waters of ML interpretability with Jessica Schrouff.Jessica is a Senior Research Scientist at Google Research w...
Continual Learning with Iman Mirzadeh
02 May 2022
Contributed by Lukas
This is a conversation between data scientist Ankush Garg, from Telepath, and fourth-year Ph.D. student Iman Mirzadeh and they’ll be talking about C...
MLOps: Research and Vision
27 Apr 2022
Contributed by Lukas
Today we’re talking about MLOps - with our guide Georgios Symeonidis and we’ll be orienting around a recent paper he published titled “MLOps - D...
Curriculum Learning in AutoML
08 Mar 2022
Contributed by Lukas
This episode covers the relationship between Curriculum Learning and AutoML with Lucas Nildaimon dos Santos Silva.Lucas is a data scientist at america...
Statistical Physics and Inference Problems
26 Feb 2022
Contributed by Lukas
In this episode, we explore the relationship between Machine Learning and Statistical Mechanics with the guidance of Alia Abbara. This conversation ce...