Programmers and researchers are increasingly developing surrogates of
pr...
In this extended abstract, we discuss the opportunity to formally verify...
Quantum algorithms for factorization, search, and simulation obtain
comp...
In reinforcement learning, the classic objectives of maximizing discount...
Datacenter operators ensure fair and regular server maintenance by using...
Practitioners frequently observe that pruning improves model generalizat...
Efficient inference is often possible in a streaming context using
Rao-B...
Emerging quantum algorithms for problems such as element distinctness, s...
Quantum programming languages enable developers to implement algorithms ...
Modern computer systems need to execute under strict safety constraints
...
Sample-efficient machine learning (SEML) has been widely applied to find...
Surrogates, models that mimic the behavior of programs, form the basis o...
In recent years, researchers have made significant progress in devising
...
Probabilistic programming languages aid developers performing Bayesian
i...
Magnitude pruning is a common, effective technique to identify sparse
su...
Computer programs are increasingly being deployed in partially-observabl...
The computer vision world has been re-gaining enthusiasm in various
pre-...
CPU simulators are useful tools for modeling CPU execution behavior. How...
Recent work has explored the possibility of pruning neural networks at
i...
In natural language processing (NLP), enormous pre-trained models like B...
A Reduction – an accumulation over a set of values, using an associative...
Deep learning is moving towards increasingly sophisticated optimization
...
We show that the error of magnitude-pruned networks follows a scaling la...
In this paper, we demonstrate a compiler that can optimize sparse and
re...
Many neural network pruning algorithms proceed in three steps: train the...
We introduce "instability analysis," a framework for assessing whether t...
Synchronous reactive languages were introduced for designing and impleme...
Recent work on the "lottery ticket hypothesis" proposes that
randomly-in...
When a computational task tolerates a relaxation of its specification or...
Statically estimating the number of processor clock cycles it takes to
e...
Researchers have recently designed a number of application-specific faul...
Researchers have recently proposed several systems that ease the process...
Though many safety-critical software systems use floating point to repre...
In this position paper, we describe our vision of the future of machine
...
In this position paper, we describe our vision of the future of machine-...
Neural network compression techniques are able to reduce the parameter c...
Recent work on neural network pruning indicates that, at training time,
...