Machine Learning Engineer: 1st July 2025

Normalizing Flows Are Capable Generative Models (machinelearning​.apple​.com). TarFlow, a Transformer-based Normalizing Flows model, achieves state-of-the-art results in likelihood estimation and image generation with advanced techniques for improved quality

Scaling Pinterest ML Infrastructure with Ray: From Training to End-to-End ML Pipelines (medium​.com/pinterest-engineering). Pinterest optimizes ML infrastructure using Ray, enhancing feature development, sampling, and labeling while achieving faster iteration and reduced costs

Using generative AI to do multimodal information retrieval (amazon​.science). GENIUS model enhances multimodal information retrieval using generative AI, outperforming traditional methods in speed and accuracy with innovative techniques like semantic quantization

DiLoCoX: A Low-Communication Large-Scale Training Framework for Decentralized Cluster (arxiv:cs). DiLoCoX framework enables decentralized training of 100B+ parameter models over slow networks, utilizing Pipeline Parallelism and Adaptive Gradient Compression for efficiency

Interpretable Representation Learning for Additive Rule Ensembles (arxiv:cs). Enhanced interpretable additive ensembles leverage learnable sparse linear transformations for rule conditions, improving model complexity and performance in predictive tasks across various datasets

dreaMLearning: Data Compression Assisted Machine Learning (arxiv:cs). dreaMLearning framework utilizes Entropy-based Generalized Deduplication for efficient machine learning, accelerating training, reducing memory usage, and enhancing scalability for diverse applications

Extreme Learning Machines for Exoplanet Simulations: A Faster, Lightweight Alternative to Deep Learning (arxiv:astro). Extreme Learning Machines outperform deep learning for exoplanet simulations, achieving significant speed improvements and varying sample efficiency across structured data types

Demystifying Distributed Training of Graph Neural Networks for Link Prediction (arxiv:cs). Distributed GNN training for link prediction faces performance degradation due to graph partitioning and negative sampling; SpLPG mitigates this with reduced communication costs

Training Flexible Models of Genetic Variant Effects from Functional Annotations using Accelerated Linear Algebra (arxiv:cs). DeepWAS leverages fast linear algebra for flexible neural network models to predict genetic variant impacts on phenotypes, enhancing disease prediction and therapeutic targeting

Towards Interpretable and Efficient Feature Selection in Trajectory Datasets: A Taxonomic Approach (arxiv:cs). Taxonomy-based feature selection improves interpretability and efficiency in trajectory datasets by organizing features into geometric and kinematic categories, enhancing predictive performance

Efficient and Reuseable Cloud Configuration Search Using Discovery Spaces (arxiv:cs). Discovery Space abstraction improves cloud resource configuration search efficiency, enabling knowledge transfer and reducing optimization time by over 90% for diverse workloads

Unimodal Strategies in Density-Based Clustering (arxiv:cs). Density-based clustering strategies improve parameter tuning for high-dimensional data using unimodal properties and Ternary Search algorithms across NLP, Audio, and Computer Vision tasks

The Most Important Features in Generalized Additive Models Might Be Groups of Features (arxiv:cs). Introducing a method for assessing group feature importance in Generalized Additive Models, enhancing insights in multimodal datasets and health outcome studies

The kernel of graph indices for vector search (arxiv:cs). Introduction of Support Vector Graph (SVG) for vector search in metric/non-metric spaces, leveraging kernel methods, enhancing graph indices like HNSW and DiskANN

Can Your Data Be Trusted Enough to Scale AI? (tigranmuradyants​.com). Trust in data is essential for scaling AI. Issues arise when teams prioritize deadlines over data quality, leading to unreliability in AI models and systems

Holden Karau (usesthis​.com). Holden Karau, Apache Spark developer, shares insights on his hardware setup, software preferences, and personal projects like technical book writing and a queer motorcycle club

Patients want to know what information an AI model considers (ehudreiter​.com). Adarsa Sivaprasad's research reveals patients prioritize understanding AI model feature considerations over operational mechanics, highlighting a need for tailored explanations in healthcare AI

Thank you, Databend; Hello, LanceDB (xuanwo​.io). Xuanwo transitions from Databend to LanceDB, focusing on open-source multimodal databases, Rust optimizations, and personal milestones in tech and life

2025-06-24: GPU Hours Granted on Hypothesis Generation by Oak Ridge Leadership Computing Facility (ws-dl​.blogspot​.com). LAMP-SYS Lab awarded GPU hours for hypothesis generation using expert LLMs, enhancing novelty assessment via Z-scores and cross-domain approach

Polars Boosted My Algorithm's Speed by 25x (john​.soban​.ski). Polars library enhances algorithm speed by 25x, outperforming Pandas with parallel processing and Apache Arrow in Reduced Columb Energy classification

Scaling Pinterest ML Infrastructure with Ray: From Training to End-to-End ML Pipelines (medium​.com/pinterest-engineering). Pinterest optimizes ML infrastructure using Ray, enhancing feature development, sampling, and labeling while achieving faster iteration and reduced costs

Pipelining AI/ML Training Workloads with CUDA Streams (towardsdatascience​.com). Explore CUDA streams for pipelining AI/ML training workloads, enhancing performance in PyTorch models through concurrent GPU operations and data augmentation techniques

A Caching Strategy for Identifying Bottlenecks on the Data Input Pipeline (towardsdatascience​.com). Explore caching strategies to identify data pipeline bottlenecks in GPU-centric machine learning workflows using PyTorch for improved performance and efficiency

Building a dynamic inventory optimisation system: A deep dive (engineering​.zalando​.com). Dynamic inventory optimization system at Zalando using AI, MLForecast, LightGBM, and AWS tools to enhance e-commerce supply chain efficiency

#511: From Notebooks to Production Data Science Systems (talkpython​.fm). Catherine Nelson discusses transitions from exploratory data science to production workflows, emphasizing code quality, software engineering practices, and MLOps platforms

Pareto ML Deployments (gojiberries​.io). Instance-level routing enhances ML model deployment, preventing regressions while balancing operational complexity and accuracy improvements on datasets like Adult income

Deploying Scikit-Learn Models for In-Database Scoring with Snowflake (posit​.co). Implement Scikit-Learn model deployment for in-database scoring with Snowflake, optimizing data management in RStudio and Jupyter environments through Posit's tools

New Dataset Using Deep Learning to Predict Permafrost Thaw Damage in the Arctic with Elias Manos (arcticdata​.io). Elias Manos develops a deep learning model for predicting permafrost thaw damage in Arctic communities, addressing infrastructure risk and environmental changes

Can We Profit from Disagreements Between Machine Learning and Trend-Following Models? (quantpedia​.com). Exploration of using ML and trend-following models for equity returns, identifying profitable discrepancies for tactical allocation

Unlocking the Secrets of Bulk Metallic Glass with Graph Computing (themultidisciplinarian​.com). Explore bulk metallic glass properties, design challenges, and the role of graph computing and machine learning in optimizing advanced materials

Could AI help us better understand the universe? (astronomy​.com). AI enhances precision in measuring cosmological parameters like dark matter and energy, offering cost-effective insights into the universe's behavior, led by Shirley Ho

Predicting Average IMDb Movie Ratings Using Text Embeddings of Movie Metadata (minimaxir​.com). Predicting IMDb movie ratings using text embeddings from metadata; explores neural networks, LLMs, and data wrangling with Polars

Vector Embeddings Explained (opencv​.org). Explore vector embeddings, their generation, and applications in semantic search, recommendation systems, and AI technology using models like Word2Vec, GloVe, and BERT

The Bitter Lesson is coming for Tokenization (lucalp​.dev). Exploring the fragility of tokenization and the promise of the Byte Latent Transformer in addressing compute and data inefficiencies in LLMs

Vectorize ROC Curve for Bayesian Models (juanitorduz​.github​.io). Vectorizing ROC curve computation for Bayesian models using Gaussian processes and the moons dataset with PyMC, ArviZ, and scikit-learn

Calculus Phobic’s Introduction to Differentiable Programming (andersource​.dev). Introduction to differentiable programming using JAX, focusing on optimization techniques, gradient descent, and automatic differentiation principles for solving computational problems

Logistic regression - a simple briefing (blog​.engora​.com). Exploration of logistic regression for binary classification, odds ratios, sigmoid function, maximum likelihood estimation using Python's scikit-learn, and extensions to multiple classifications

False Causes, Meet Attractor Dimension (methodsblog​.com). Yair Daon explores causation in public health using attractor dimensions, proposing BCAD for rejecting false causal links in ecological data analysis

(Don't) Forget About It: Toward Pareto-Improving GD (gojiberries​.io). Exploration of catastrophic forgetting in machine learning and methods to reduce regression during model training with a focus on loss function modifications

Log-ish (johndcook​.com). Explores logarithmic transformations like log(1 + x) for handling both positive and negative values, alongside alternatives like arcsinh and softplus

Researchers Uncover Hidden Ingredients Behind AI Creativity (quantamagazine​.org). Study reveals diffusion models' creativity stems from architectural imperfections in denoising, linking AI creativity with local patch processing techniques

Get ready for the PDE-Transformer (ge​.in​.tum​.de). Introducing PDE-Transformer: a novel architecture for physics simulations, combining UDiT and SWin features, outperforming existing methods in diverse PDE datasets

Normalizing Flows Are Capable Generative Models (machinelearning​.apple​.com). TarFlow, a Transformer-based Normalizing Flows model, achieves state-of-the-art results in likelihood estimation and image generation with advanced techniques for improved quality

I've got a big favor to ask - keeping Blaze running isn't expensive, but it does all add up, so I'm asking readers like you to help, if you can.
That's why I'm launching a Patreon page!. Nothing flashy, just a way for folks who find value in these newsletters to chip in a little each month. In return, you'll get:

• Real say in how Blaze evolves — vote on new topics, features, topic curation ideas
• First dibs on merch (details still cooking)
• That warm fuzzy feeling knowing you're supporting something that saves you time and keeps you plugged into great tech writing

If you are getting value from blaze, checking this out would mean the world. And if you can't contribute, no worries—the newsletters keep coming either way, and you can follow along on patreon for free.
Thanks for reading and being part of this nerdy corner of the internet. All the best - Alastair.