Related papers: COMET: Neural Cost Model Explanation Framework

During early optimization passes, compilers must make predictions for machine-dependent characteristics such as execution unit utilization, number of register spills, latency, throughput etc. to generate better code. Often a hand-written…

There has been significant research over the past two decades in developing new platforms for spiking neural computation. Current neural computers are primarily developed to mimick biology. They use neural networks which can be trained to…

Data quality is crucial in machine learning (ML) applications, as errors in the data can significantly impact the prediction accuracy of the underlying ML model. Therefore, data cleaning is an integral component of any ML pipeline. However,…

Advances in deep learning have led to substantial increases in prediction accuracy but have been accompanied by increases in the cost of rendering predictions. We conjecture that fora majority of real-world inputs, the recent advances in…

Recently Quantum Computation has generated a lot of interest due to the discovery of a quantum algorithm which can factor large numbers in polynomial time. The usefulness of a quantum com puter is limited by the effect of errors. Simulation…

The development of concurrent applications is challenging because of the complexity of concurrent designs and the hazards of concurrent programming. Architectural modeling using the Unified Modeling Language (UML) can support the…

We propose a novel, flexible, and efficient framework for designing Concept Bottleneck Models (CBMs) that enables practitioners to explicitly encode and extend their prior knowledge and beliefs about the concept-concept ($C-C$) and…

A growing body of research in continual learning focuses on the catastrophic forgetting problem. While many attempts have been made to alleviate this problem, the majority of the methods assume a single model in the continual learning…

Cloud is now the leading software and computing hardware innovator, and is changing the landscape of compute to one that is optimized for artificial intelligence and machine learning (AI/ML). Computing innovation was initially driven to…

Accurate simulations of atomistic systems from first principles are limited by computational cost. In high-throughput settings, machine learning can reduce these costs significantly by accurately interpolating between reference…

Concept Bottleneck Models (CBMs) provide a basis for semantic abstractions within a neural network architecture. Such models have primarily been seen through the lens of interpretability so far, wherein they offer transparency by inferring…

Concept Bottleneck Model (CBM) is a methods for explaining neural networks. In CBM, concepts which correspond to reasons of outputs are inserted in the last intermediate layer as observed values. It is expected that we can interpret the…

Model Interpretation aims at the extraction of insights from the internals of a trained model. A common approach to address this task is the characterization of relevant features internally encoded in the model that are critical for its…

We present two metalanguages for developing $\textit{synthetic cost-aware denotational semantics}$ of programming languages. Extending the recent work of Niu et al. [2022] on $\textbf{calf}$, a dependent type theory for both cost and…

Large reasoning models (LRMs) improve problem solving through extended reasoning, but often misallocate test-time compute. Existing efficiency methods reduce cost by compressing reasoning traces or conditioning budget on perceived…

Accounting for the uncertainty in the predictions of modern neural networks is a challenging and important task in many domains. Existing algorithms for uncertainty estimation require modifying the model architecture and training procedure…

Bayesian parameter inference is an essential tool in modern cosmology, and typically requires the calculation of $10^5$--$10^6$ theoretical models for each inference of model parameters for a given dataset combination. Computing these…

In the framework of risk assessment in nuclear accident analysis, best-estimatecomputer codes, associated to a probabilistic modeling of the uncertain input variables,are used to estimate safety margins. A first step in such uncertainty…

Predictive models are often used for real-time decision making. However, typical machine learning techniques ignore feature evaluation cost, and focus solely on the accuracy of the machine learning models obtained utilizing all the features…

Computational models in chemistry rely on a number of approximations. The effect of such approximations on observables derived from them is often unpredictable. Therefore, it is challenging to quantify the uncertainty of a computational…