Related papers: Optimizing Sparse Linear Algebra Through Automatic…
In recent years, many accelerators have been proposed to efficiently process sparse tensor algebra applications (e.g., sparse neural networks). However, these proposals are single points in a large and diverse design space. The lack of…
We learn optimal instance-specific heuristics for the global minimization of nonconvex quadratically-constrained quadratic programs (QCQPs). Specifically, we consider partitioning-based convex mixed-integer programming relaxations for…
When designing new materials, it is often necessary to design a material with specific desired properties. Unfortunately, as new design variables are added, the search space grows exponentially, which makes synthesizing and validating the…
Machine learning (ML) methods are used in most technical areas such as image recognition, product recommendation, financial analysis, medical diagnosis, and predictive maintenance. An important aspect of implementing ML methods involves…
We develop Morphlux, a server-scale programmable photonic fabric to interconnect accelerators within servers. We show that augmenting state-of-the-art torus-based ML data-centers with Morphlux can improve the bandwidth of tenant compute…
Automatic performance tuning (auto-tuning) is widely used to optimize performance-critical applications across many scientific domains by finding the best program variant among many choices. Efficient optimization algorithms are crucial for…
As neural network model sizes have dramatically increased, so has the interest in various techniques to reduce their parameter counts and accelerate their execution. An active area of research in this field is sparsity - encouraging zero…
Sparse Autoencoders (SAEs) have proven to be powerful tools for interpreting neural networks by decomposing hidden representations into disentangled, interpretable features via sparsity constraints. However, conventional SAEs are…
Linear algebra algorithms are used widely in a variety of domains, e.g machine learning, numerical physics and video games graphics. For all these applications, loop-level parallelism is required to achieve high performance. However,…
Automated machine learning (AutoML) has democratized the design of machine learning based systems, by automating model selection, hyperparameter tuning and feature engineering. However, the high computational cost associated with…
In this paper, we introduce a novel approach for addressing the multi-objective optimization problem in large language model merging via black-box multi-objective optimization algorithms. The goal of model merging is to combine multiple…
Sparse Autoencoders (SAEs) can extract interpretable features from large language models (LLMs) without supervision. However, their effectiveness in downstream steering tasks is limited by the requirement for contrastive datasets or large…
Large Reasoning Models (LRMs) exhibit human-like cognitive reasoning strategies (e.g. backtracking, cross-verification) during reasoning process, which improves their performance on complex tasks. Currently, reasoning strategies are…
Designing reliable integrated energy systems for industrial processes requires optimization and verification models across multiple fidelities, from architecture-level sizing to high-fidelity dynamic operation. However, model mismatch…
The escalating size of Mixture-of-Experts (MoE) based Large Language Models (LLMs) presents significant computational and memory challenges, necessitating innovative solutions to enhance efficiency without compromising model accuracy.…
The study of healthy brain development helps to better understand the brain transformation and brain connectivity patterns which happen during childhood to adulthood. This study presents a sparse machine learning solution across whole-brain…
Widely used compilers like GCC and LLVM usually have hundreds of optimizations controlled by optimization flags, which are enabled or disabled during compilation to improve runtime performance (e.g., small execution time) of the compiler…
We propose a sparse algebra for samplet compressed kernel matrices, to enable efficient scattered data analysis. We show the compression of kernel matrices by means of samplets produces optimally sparse matrices in a certain S-format. It…
Muon improves neural-network training by orthogonalizing matrix-valued updates, but it leaves each layer's update magnitude controlled mostly by a global learning rate. We introduce OrScale, a trust-ratio extension of Muon built on a simple…
Optimization problems are pervasive in sectors from manufacturing and distribution to healthcare. However, most such problems are still solved heuristically by hand rather than optimally by state-of-the-art solvers because the expertise…