Search Results for author:
Found 17 papers, 8 papers with code
Incremental IVF Index Maintenance for Streaming Vector Search
The prevalence of vector similarity search in modern machine learning applications and the continuously changing nature of data processed by these applications necessitate efficient and effective index maintenance techniques for vector search indexes.
Co-design Hardware and Algorithm for Vector Search
Vector search has emerged as the foundation for large-scale information retrieval and machine learning systems, with search engines like Google and Bing processing tens of thousands of queries per second on petabyte-scale document datasets by evaluating vector similarities between encoded query texts and web documents.
Stochastic Gradient Descent without Full Data Shuffle
In this paper, we first conduct a systematic empirical study on existing data shuffling strategies, which reveals that all existing strategies have room for improvement -- they all suffer in terms of I/O performance or convergence rate.
SHiFT: An Efficient, Flexible Search Engine for Transfer Learning
Transfer learning can be seen as a data- and compute-efficient alternative to training models from scratch.
Learning to Merge Tokens in Vision Transformers
Transformers are widely applied to solve natural language understanding and computer vision tasks.
Dynamic Human Evaluation for Relative Model Comparisons
Collecting human judgements is currently the most reliable evaluation method for natural language generation systems.
Evaluating Bayes Error Estimators on Real-World Datasets with FeeBee
The Bayes error rate (BER) is a fundamental concept in machine learning that quantifies the best possible accuracy any classifier can achieve on a fixed probability distribution.
Decoding EEG Brain Activity for Multi-Modal Natural Language Processing
In this paper, we present the first large-scale study of systematically analyzing the potential of EEG brain activity data for improving natural language processing tasks, with a special focus on which features of the signal are most beneficial.
A Data Quality-Driven View of MLOps
Developing machine learning models can be seen as a process similar to the one established for traditional software development.
Automatic Feasibility Study via Data Quality Analysis for ML: A Case-Study on Label Noise
In our experience of working with domain experts who are using today's AutoML systems, a common problem we encountered is what we call "unrealistic expectations" -- when users are facing a very challenging task with a noisy data acquisition process, while being expected to achieve startlingly high accuracy with machine learning (ML).
On Convergence of Nearest Neighbor Classifiers over Feature Transformations
This analysis requires in-depth understanding of the properties that connect both the transformed space and the raw feature space.
Which Model to Transfer? Finding the Needle in the Growing Haystack
Transfer learning has been recently popularized as a data-efficient alternative to training models from scratch, in particular for computer vision tasks where it provides a remarkably solid baseline.
Scalable Transfer Learning with Expert Models
We explore the use of expert representations for transfer with a simple, yet effective, strategy.
Ranked #8 on
Image Classification
on VTAB-1k
(using extra training data)
Observer Dependent Lossy Image Compression
To that end, we use a family of loss functions that allows to optimize deep image compression depending on the observer and to interpolate between human perceived visual quality and classification accuracy, enabling a more unified view on image compression.
Continuous Integration of Machine Learning Models with ease.ml/ci: Towards a Rigorous Yet Practical Treatment
Continuous integration is an indispensable step of modern software engineering practices to systematically manage the life cycles of system development.
Distributed Learning over Unreliable Networks
Most of today's distributed machine learning systems assume {\em reliable networks}: whenever two machines exchange information (e. g., gradients or models), the network should guarantee the delivery of the message.
SparCML: High-Performance Sparse Communication for Machine Learning
This allreduce is the single communication and thus scalability bottleneck for most machine learning workloads.
