Search Results for author:
Found 22 papers, 5 papers with code
LLM-Pilot: Characterize and Optimize Performance of your LLM Inference Services
The performance of an LLM inference service is largely determined by the hardware onto which it is deployed, but understanding of which hardware will deliver on performance requirements remains challenging.
Accelerating Production LLMs with Combined Token/Embedding Speculators
This technical report describes the design and training of novel speculative decoding draft models, for accelerating the inference speeds of large language models in a production environment.
Search-based Methods for Multi-Cloud Configuration
Our experiments indicate that (a) many state-of-the-art cloud configuration solutions can be adapted to multi-cloud, with best results obtained for adaptations which utilize the hierarchical structure of the multi-cloud configuration domain, (b) hierarchical methods from AutoML can be used for the multi-cloud configuration task and can outperform state-of-the-art cloud configuration solutions and (c) CB achieves competitive or lower regret relative to other tested algorithms, whilst also identifying configurations that have 65% lower median cost and 20% lower median time in production, compared to choosing a random provider and configuration.
What can multi-cloud configuration learn from AutoML?
Multi-cloud computing has become increasingly popular with enterprises looking to avoid vendor lock-in.
Towards a General Framework for ML-based Self-tuning Databases
Machine learning (ML) methods have recently emerged as an effective way to perform automated parameter tuning of databases.
SnapBoost: A Heterogeneous Boosting Machine
At each boosting iteration, their goal is to find the base hypothesis, selected from some base hypothesis class, that is closest to the Newton descent direction in a Euclidean sense.
Differentially Private Stochastic Coordinate Descent
In this paper we tackle the challenge of making the stochastic coordinate descent algorithm differentially private.
SySCD: A System-Aware Parallel Coordinate Descent Algorithm
In this paper we propose a novel parallel stochastic coordinate descent (SCD) algorithm with convergence guarantees that exhibits strong scalability.
Breadth-first, Depth-next Training of Random Forests
In this paper we analyze, evaluate, and improve the performance of training Random Forest (RF) models on modern CPU architectures.
Weighted Sampling for Combined Model Selection and Hyperparameter Tuning
In this work, we propose a novel sampling distribution as an alternative to uniform sampling and prove theoretically that it has a better chance of finding the best configuration in a worst-case setting.
Learning to Tune XGBoost with XGBoost
In this short paper we investigate whether meta-learning techniques can be used to more effectively tune the hyperparameters of machine learning models using successive halving (SH).
Addressing Algorithmic Bottlenecks in Elastic Machine Learning with Chicle
To address this, we propose Chicle, a new elastic distributed training framework which exploits the nature of machine learning algorithms to implement elasticity and load balancing without micro-tasks.
5 Parallel Prism: A topology for pipelined implementations of convolutional neural networks using computational memory
We show that this communication fabric facilitates the pipelined execution of all state of-the-art CNNs by proving the existence of a homomorphism between one graph representation of these networks and the proposed graph topology.
Sampling Acquisition Functions for Batch Bayesian Optimization
We present Acquisition Thompson Sampling (ATS), a novel technique for batch Bayesian Optimization (BO) based on the idea of sampling multiple acquisition functions from a stochastic process.
Elastic CoCoA: Scaling In to Improve Convergence
In this paper we experimentally analyze the convergence behavior of CoCoA and show, that the number of workers required to achieve the highest convergence rate at any point in time, changes over the course of the training.
Parallel training of linear models without compromising convergence
The combined set of optimizations result in a consistent bottom line speedup in convergence of up to 12x compared to the initial asynchronous parallel training algorithm and up to 42x, compared to state of the art implementations (scikit-learn and h2o) on a range of multi-core CPU architectures.
Benchmarking and Optimization of Gradient Boosting Decision Tree Algorithms
Gradient boosting decision trees (GBDTs) have seen widespread adoption in academia, industry and competitive data science due to their state-of-the-art performance in many machine learning tasks.
Snap ML: A Hierarchical Framework for Machine Learning
We describe a new software framework for fast training of generalized linear models.
Efficient Use of Limited-Memory Accelerators for Linear Learning on Heterogeneous Systems
We propose a generic algorithmic building block to accelerate training of machine learning models on heterogeneous compute systems.
Large-Scale Stochastic Learning using GPUs
In this work we propose an accelerated stochastic learning system for very large-scale applications.
Understanding and Optimizing the Performance of Distributed Machine Learning Applications on Apache Spark
We begin by analyzing the characteristics of a state-of-the-art distributed machine learning algorithm implemented in Spark and compare it to an equivalent reference implementation using the high performance computing framework MPI.
Scalable and interpretable product recommendations via overlapping co-clustering
We consider the problem of generating interpretable recommendations by identifying overlapping co-clusters of clients and products, based only on positive or implicit feedback.
