article Mar 13, 2025How Boosted Decision Trees can Benefit from Language ModelsThere has been a lot of progress in natural language understanding during the last years. Let it be the rise of AI assistants like ChatGPT or most recently in foundational models like ModernBERT.[... 981 words]data-sciencenlupythonllmgbdtmachine-learning
article Mar 20, 2024Optimizing Data Loading and GPU Usage in PyTorchToday, it’s not too uncommon to have data processing tasks—including training neural networks—that require a GPU to finish in a reasonable amount of time. Acquiring one is fairly straightforward thanks to the abundance of cloud providers like AWS, GCP, Paperspace, and so on.[... 445 words]machine-learningpytorchperformance-tuningneural-networks
article Dec 20, 2023Enhance Training Speed with Mixed Precision TrainingIf your data loading is efficient and GPU utilization is almost always at 100%, it is time to consider speeding up the actual computation that happens there. Note that most operations on the GPU involve dealing with floating point variables (activations, gradients, and so on), each having a certain precision – most commonly float32 (or full precision).[... 353 words]machine-learningneural-networksperformance-tuning
article Oct 04, 2023Optional Sampling for Better Feedback LoopsThe main difference between machine learning applications and regular software is the dependence on a larger amount of (historical) data. With regards to speeding up the development process, a key insight is that it is usually not necessary to use all the data at every step.[... 481 words]machine-learningsql
article Jun 11, 2023Reducing Memory Requirements with Sparse Data StructuresUsing sparse data structures can vastly reduce memory requirements. Sparse data refers to data where most entries are zero, while dense data contains a higher proportion of non-zero values.[... 283 words]data-engineeringdata-scienceperformance-tuningmachine-learning