Search Results for author:
Found 13 papers, 8 papers with code
GPT-4o System Card
We also include third-party assessments on dangerous capabilities, as well as discussion of potential societal impacts of GPT-4o's text and vision capabilities.
Ranked #2 on
Multiple-choice
on Neptune-Full
The Next 700 ML-Enabled Compiler Optimizations
There is a growing interest in enhancing compiler optimizations with ML models, yet interactions between compilers and ML frameworks remain challenging.
Kepler: Robust Learning for Faster Parametric Query Optimization
We propose Kepler, an end-to-end learning-based approach to PQO that demonstrates significant speedups in query latency over a traditional query optimizer.
A Transferable Approach for Partitioning Machine Learning Models on Multi-Chip-Modules
Partitioning ML graphs for MCMs is particularly hard as the search space grows exponentially with the number of chiplets available and the number of nodes in the neural network.
Differentiable Architecture Search for Reinforcement Learning
In this paper, we investigate the fundamental question: To what extent are gradient-based neural architecture search (NAS) techniques applicable to RL?
Reverb: A Framework For Experience Replay
A central component of training in Reinforcement Learning (RL) is Experience: the data used for training.
MLGO: a Machine Learning Guided Compiler Optimizations Framework
Leveraging machine-learning (ML) techniques for compiler optimizations has been widely studied and explored in academia.
Sample-Efficient Reinforcement Learning with Stochastic Ensemble Value Expansion
Integrating model-free and model-based approaches in reinforcement learning has the potential to achieve the high performance of model-free algorithms with low sample complexity.
Dynamic Control Flow in Large-Scale Machine Learning
We describe the design of the programming model, and its implementation in TensorFlow, a distributed machine learning system.
Tensor2Tensor for Neural Machine Translation
Tensor2Tensor is a library for deep learning models that is well-suited for neural machine translation and includes the reference implementation of the state-of-the-art Transformer model.
TensorFlow Distributions
The TensorFlow Distributions library implements a vision of probability theory adapted to the modern deep-learning paradigm of end-to-end differentiable computation.
Deep Probabilistic Programming
By treating inference as a first class citizen, on a par with modeling, we show that probabilistic programming can be as flexible and computationally efficient as traditional deep learning.
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
TensorFlow is an interface for expressing machine learning algorithms, and an implementation for executing such algorithms.
