PinnedJordan TotteninScaling ML workloads with Google CloudScaling deep retrieval with TensorFlow Recommenders and Vertex AI Vector SearchHow to build two-tower encoders for large-scale candidate retrieval, and optimize for low-latency servingApr 16Apr 16
Jordan TottenOne way to think about Reinforcement Learning for Recommender SystemsApplying reinforcement learning- (RL) based techniques to recommender systems (RecSys) has gained increased attention over the years. And…Jun 21Jun 21
Jordan TotteninScaling ML workloads with Google CloudScaling deep learning workloads with PyTorch / XLA and Cloud TPU VM | Google Cloud BlogAddressing data input pipeline bottlenecks for distributed and accelerated jobs that stream training data from remote storageApr 16Apr 16