This research simplifies computation of feature attribution methods under certain conditions.
problem Computational complexity of feature attribution methods, especially power indices.
method Identifying conditions for polynomial computation and introducing new indices.
result Conditions for efficient computation of feature attribution methods are identified.
Finite precision RNNs have varying computational power, with LSTMs and ReLU-RNNs being more powerful.
problem Understanding the computational limits of finite precision RNNs for language recognition.
method Comparison of different RNN variants with finite precision and linear computation time.
result LSTMs and ReLU-RNNs are strictly stronger than other RNN variants in terms of computational power.
Paper develops geometric tools for power flow analysis.
problem Analyzing the boundary of power flow solution space.
method Differential geometric analysis of power flow solution space boundary.
result New high precision continuation method and geodesic coordinates.
This paper considers the computational power of constant size, dynamic Bayesian networks. Although discrete dynamic Bayesian networks are no more powerful than hidden Markov models, dynamic Bayesian networks with continuous random variables and discrete children of continuous parents are capable of performing Turing-co…
Deep learning's success requires vast computing power, making future progress unsustainable.
problem Deep learning's success is heavily dependent on computing power, making future progress unsustainable.
method Cataloging and extrapolating the dependency on computing power for various deep learning applications.
result Continued progress in deep learning applications will require more computationally-efficient methods.
A DRL approach optimizes computation offloading in MEC systems for mobile users.
problem Optimizing computation offloading in MEC systems with mobile users and stochastic task arrivals.
method Deep Deterministic Policy Gradient (DDPG) for decentralized dynamic computation offloading.
result The DDPG-based strategy outperforms conventional strategies in terms of computation cost and power-delay tradeoff.
MONAS optimizes neural architectures for both accuracy and power consumption.
problem Finding efficient neural architectures for limited computing environments.
method Multi-objective reinforcement learning considering accuracy and power consumption.
result MONAS finds architectures with comparable or better accuracy and lower power consumption.
Improves RNN performance under noisy computations.
problem Power and speed limitations in deep learning with noisy analog circuits.
method Deep Noise Injection training to robustify RNN weights/biases.
result Trained RNNs show more consistent performance under noisy inference.
Study shows limits of certain normalizing flows in higher dimensions.
problem Understanding the representation power of normalizing flows in different dimensions.
method Rigorously established bounds on expressive power of basic normalizing flows.
result Limited representation power in higher dimensions, especially with moderate depth.
FPGA-based logic architecture speeds up GBDT training 259x.
problem Training efficiency and power consumption in GBDT models.
method Implemented logic architecture on FPGA, compared with software libraries.
result Training speed 26-259x faster, power efficiency 90-1,104x higher.
Statistical learning improves reactive power control in distribution systems.
problem Challenges in reactive power control due to renewable energy sources and flexible loads.
method A deep neural network parameterizes the input-output relationship between grid states and optimal reactive power control. Unknown weights are learned offline to minimize power loss, and inference is fast with matrix-vector multiplications.
result Computational efficiency and robustness to random input perturbations demonstrated in a 47-bus distribution network.
A power-law fit to the empirical inference-compute frontier in LOB prediction suggests a scaling-law-style frontier.
problem Limit order book prediction
method Using a suite of models ranging from small decision trees to neural LOB architectures
result A power-law fit to the low- and mid-compute non-MLPLOB frontier extrapolates across multiple orders of magnitude and attains R2=0.941 on the excluded high-compute MLPLOB target frontier. Paper uses ensemble learning for more accurate power flow modeling.
problem Improving accuracy and efficiency of power flow modeling.
method Applies polynomial regression and ensemble learning (GB, bagging) to create a more accurate linear power flow model.
result Data-driven model outperforms traditional methods in accuracy and speed.
Blockchain as a Service offers a secure, decentralized computing solution.
problem Lack of transparency, security, and privacy in cloud computing.
method Decentralized cooperative computing process using blockchain, homomorphic encryption, and SDN.
result Performance evaluated via different scenarios in simulations.
Proposes using Banzhaf power indices for feature importance and pruning in machine learning.
problem Understanding and selecting important features in machine learning models.
method Uses principles from coalitional game theory, specifically Banzhaf power index, to measure feature importance and prune features without loss of accuracy.
result Features with zero Banzhaf power index can be losslessly pruned without affecting classifier accuracy.
Implicit models can match or exceed explicit models with more test-time compute.
problem Understanding the expressive power and scaling of implicit models.
method Nonparametric analysis of expressive power, mathematical characterization of implicit operators, and test-time scaling experiments.
result Implicit models can progressively express more complex mappings through iteration, matching a richer function class with test-time compute.
Quantum machine learning aims to leverage quantum computing for better pattern recognition.
problem Finding patterns in data efficiently using classical computers.
method Developing and implementing quantum software to outperform classical machine learning.
result Quantum computers can potentially outperform classical ones in machine learning tasks.
Power quandles improve group invariants and allow group presentations.
problem Understanding and classifying groups using algebraic structures.
method Introducing power quandles, which retain conjugation and power maps, and showing their effectiveness in group theory.
result Power quandles determine central quotients and centers of groups, and can approximate any group.
The loop invariants of Dimofte-Garoufalidis is a formal power series with arithmetically interesting coefficients that conjecturally appears in the asymptotics of the Kashaev invariant of a knot to all orders in 1/N. We develop methods implemented in SnapPy that compute the first 6 coefficients of the formal power se…
Power weighted shortest paths improve clustering of high-dimensional data.
problem Clustering high-dimensional Euclidean data with disjoint low-dimensional manifolds.
method Use of power weighted shortest path distance functions and a fast algorithm.
result Higher clustering accuracy achieved through power weighted shortest paths.
A framework combines diverse power grid data for a unified view.
problem Unified view of complex power grids with distributed resources.
method Belief Propagation for probabilistic data fusion.
result Efficient distributed inference algorithm for grid state quantification.
Efficient neural network improves disaggregation of home energy usage.
problem Estimating power consumption of individual appliances from total home power.
method Fully convolutional neural network architecture with improved computational efficiency.
result Achieves state-of-the-art disaggregation performance with reduced training and prediction times.
A new neural network method for efficient power system security analysis.
problem Efficiently compute load-flows for power system security analysis.
method Guided dropout technique to train a deep feed-forward neural network on n-1 problems.
result Generalization to n-2 problems without retraining, leveraging the combinatorial nature of the problem.
We introduce preferential behavior into the study on statistical mechanics of money circulation. The computer simulation results show that the preferential behavior can lead to power laws on distributions over both holding time and amount of money held by agents. However, some constraints are needed in generation mecha…
Introduces a new method for clustering multilayer graphs.
problem How to merge information from different layers in multilayer graphs.
method Introduces a one-parameter family of matrix power means for merging Laplacians from different layers.
result The method allows for accurate recovery of ground truth clusters under various settings.
PPI++ uses machine learning predictions to improve inference from small datasets.
problem Efficient inference from small labeled datasets with high-quality predictions.
method Adapts prediction-powered inference (PPI) to compute confidence sets for any parameter dimensionality.
result Improves classical intervals using only labeled data, always yielding better results.
We derive the implied volatility estimation formula in European power call options pricing, where the payoff functions are in the form of V=(STα−K)+ and V=(STα−Kα)+ (α>0)respectively. Using quadratic Taylor approximations, We develop the computing formula of implied volatility in European power call op…
Model shows how centralization occurs in cryptocurrency mining.
problem Centralization of reward and computational power in Bitcoin-like cryptocurrencies.
method Mean field game model to study miner competition and reward distribution.
result Heterogeneity of initial wealth leads to greater imbalance in reward distribution.
New invariants for link analysis include biquandle power brackets.
problem Analyzing oriented links with new invariants.
method Introducing biquandle power brackets as an infinite family of link invariants.
result Biquandle power brackets encompass classical and previous invariants.
Machine Learning benefits from prior information and computational power for better performance and understanding.
problem Improper use of Machine Learning methods leads to lack of understanding and performance issues.
method Employing prior information and computational power to solve learning problems, emphasizing interpretability and performance.
result Combining prior information and computational power can lead to better understanding and performance in Machine Learning.
pAElla detects malware in DCs/SCs with high accuracy.
problem Real-time malware detection in high-resolution data centers.
method AI-powered edge computing with IoT-based monitoring and Power Spectral Density.
result pAElla achieves F1-score close to 1 with low false alarm and malware miss rates.
CoNNTrA trains DNNs with low-power, low-memory constraints.
problem Training deep neural networks on edge computing systems with low power and memory usage.
method Coordinate gradient descent-based approach for training DNNs with constrained learning parameters.
result CoNNTrA models use 32x less memory and have comparable errors to Backpropagation models.
Paper proposes MAMRL for efficient energy dispatch in self-powered edge computing systems.
problem High energy consumption in self-powered edge computing systems.
method Developed a semi-distributed data-driven MAMRL framework to solve a two-stage linear stochastic programming problem.
result The proposed MAMRL framework reduces up to 11% non-renewable energy usage and 22.4% energy cost.
Optimal sampling reduces power grid data analysis costs.
problem Efficient online analysis of high-speed, correlated IoT data.
method D-optimality criterion-based sampling methods combining Bernoulli and leverage score sampling.
result Leverage score sampling improves computational efficiency and outperforms benchmarks.
Scaling laws found for reinforcement learning performance with model size and compute.
problem Challenges in extending generative modeling scaling laws to reinforcement learning.
method Introduced intrinsic performance as a monotonic function of mean episode return.
result Intrinsic performance scales as a power law in model size and environment interactions.
Innovative neural networks reduce memory usage for efficient, accurate segmentation.
problem Efficiently segmenting large graphs with limited memory.
method Iterative neural networks with loops and multiple outputs.
result State-of-the-art semantic segmentation results on demanding datasets.
A new algorithm reduces communication in distributed SVD by p factors.
problem Efficiently compute SVD in distributed systems.
method LocalPower algorithm with weighted aggregation and periodic decay of iterations.
result Reduces communication cost by a factor of p. For a symplectic manifold with quantizing line bundle, a choice of almost complex structure determines a Laplacian acting on tensor powers of the bundle. For high tensor powers Guillemin-Uribe showed that there is a well-defined cluster of low-lying eigenvalues, whose distribution is described by a spectral density fun…
Improved MMD test for two-sample testing with random Fourier features.
problem Quadratic-time complexity of MMD test for large-scale analysis.
method Approximated MMD test using random Fourier features, investigating time-power trade-off.
result Sub-quadratic time complexity with same minimax separation rates as MMD test.
G-computation improves clinical trial power with machine learning.
problem Balancing prognostic factors in randomized trials to prevent near-confounders.
method G-computation with penalized models (Lasso, Elasticnet) and algorithm-based methods (neural network, SVM, super learner).
result G-computation with Elasticnet and splines reduces variance and increases power in RCTs.
Valid inference from data and predictions.
problem Valid statistical inference with machine learning predictions.
method Framework for valid inference using machine learning predictions.
result Valid confidence intervals without assumptions on predictions.
Proposes a spiking neural network for efficient classification.
problem High computational and power costs of ANNs.
method Random Neural Network (RNN) with spiking neurons.
result Matches classification power of ANNs but with lower energy consumption.
The paper calculates asymptotic expansions for specific types of oscillatory integrals.
problem Analyzing oscillatory integrals with complex phase functions.
method Using asymptotic expansions of simpler phase functions to derive results for more complex cases.
result Explicit computation of coefficients in asymptotic expansions for certain integrals.
LIQSS method improves accuracy and efficiency for power system simulations.
problem Accurately modeling and simulating long-duration mission profiles of Naval power systems.
method Linear Implicit Quantized State System (LIQSS) method for stiff, nonlinear, differential algebraic equations.
result LIQSS1 method yields results within 1% accuracy of continuous methods and increases efficiency logarithmically with quantization size.
Deep learning performance scales predictably with data and computation.
problem Understanding the relationship between training set size, computational scale, and model accuracy improvements.
method Empirical characterization of generalization error and model size growth across four domains: machine translation, language modeling, image processing, and speech recognition.
result Power-law generalization error scaling and sublinear model size growth with data size, with exponents not explained by theoretical work.
A new method compares synthetic power networks to actual ones using multiscale flat norm.
problem Comparing synthetic power networks to actual ones due to lack of correspondence.
method Proposes a multiscale flat norm approach to compute distance between networks.
result The flat norm distance captures variations more accurately than Hausdorff distance.
Mobile SoCs can improve ML inference by 2x when all components are used concurrently.
problem Power-performance trade-offs in mobile ML inference on heterogeneous SoCs.
method Quantitative evaluation of different ML components on mobile SoCs.
result Mobile SoCs can achieve up to 2x improvement in inference performance by using all components concurrently.
In exploratory data analysis, we are often interested in identifying promising pairwise associations for further analysis while filtering out weaker, less interesting ones. This can be accomplished by computing a measure of dependence on all variable pairs and examining the highest-scoring pairs, provided the measure o…