SIMCom detects HTs by analyzing communication patterns in SoCs.
problem Timely detection of Hardware Trojans in secure integrated circuits.
method Multi-parameter statistical modeling of communication channels in SoCs.
result SIMCom detects HTs with less than 1% area and power overhead.
Detects and mitigates rare subclasses in deep neural networks.
problem Underrepresented classes in training datasets reduce classifier performance.
method Commonality metric for detection, methods for reducing impact during training and exploitation.
result Models compensate for rare subclasses, improving performance and runtime identification.
ATSDLN adapts to time series data for anomaly detection.
problem Challenges in selecting and optimizing anomaly detectors for time series data.
method Adaptive Time Series Detector Learning Network (ATSDLN) that selects and optimizes detectors and parameters.
result ATSDLN outperforms other methods in anomaly detection across various datasets.
Quantum entropy scoring improves robust mean estimation and outlier detection.
problem Robust mean estimation and outlier detection in high-dimensional data.
method QUE-scoring based on quantum entropy regularization.
result First algorithm with optimal error rates and nearly-linear running time for robust mean estimation.
A new modularity density measure improves community detection in heterogeneous networks.
problem Detecting meaningful communities in heterogeneous networks.
method Formulated a novel metric, modularity density, for undirected, weighted networks.
result Maximization of modularity density is free from bias and better at detecting weakly-separated communities.
New CUSUM algorithm detects changes in unnormalized models.
problem Change detection in models with unknown normalization constants.
method Score-based CUSUM (SCUSUM) algorithm based on Fisher divergence and Hyvärinen score.
result Asymptotic optimality of the SCUSUM algorithm demonstrated.
Sitatapatra blocks adversarial samples across different neural networks.
problem Adversarial samples can trick multiple neural networks trained on the same task.
method Sitatapatra diversifies neural networks using a cryptographic key and detects adversarial samples.
result Sitatapatra can trace back adversarial samples to the device that created them.
A new method detects concept drift without true labels.
problem Detecting concept drift in unsupervised settings.
method Student-teacher learning paradigm for drift detection.
result The method outperforms state-of-the-art approaches in experiments.
The paper predicts run times for Gaussian chemistry code.
problem Accurate run time prediction for complex scientific codes.
method Characterized data set, explored regression methods.
result Promising future directions for run time prediction.
Proposes a fair deep anomaly detection method.
problem Ensuring fairness in deep anomaly detection.
method Adversarial network to de-correlate sensitive attributes and learned representations.
result Our approach largely removes unfairness with minimal anomaly detection performance loss.
HGConv uses HRR to efficiently detect malware, outperforming existing methods.
problem Efficiently detecting malware with long sequences.
method Holographic Global Convolutional Networks (HGConv) utilizing Holographic Reduced Representations (HRR).
result Achieved state-of-the-art results on malware benchmarks.
Deep metric learning detects anomalies without labels.
problem Unsupervised anomaly detection for high-dimensional data.
method Deep metric learning with end-to-end optimization, data distillation, hard mining.
result Significant performance gains over state-of-the-art methods.
Improved histogram-based anomaly detector using extended principal component features.
problem Challenges in detecting anomalies in large, correlated datasets.
method Extended histogram-based anomaly detection using principal components.
result Significant improvement in anomaly detection accuracy with no significant increase in runtime.
New method reduces neural image compression run-time by 50%.
problem Computational efficiency of neural image compression models.
method Automatic network optimization to reduce decoder complexity.
result Decreased decoder run-time by over 50%.
Sketch-based approach detects community events in evolving networks.
problem Community detection in time-varying networks.
method Maintains a small sketch graph to capture essential community structure.
result Efficiently identifies six key community events during network evolution.
End-to-end CNN for real-time MOD improves KITTI dataset accuracy by 8%.
problem Real-time detection of moving objects for autonomous vehicles.
method Spatio-temporal context and time-aware architecture using optical flow.
result Improvement of 8% in KITTI dataset accuracy compared to baselines.
New compression technique reduces RNN size by 2-4x without sacrificing accuracy.
problem Large and compute-intensive RNNs on edge devices with run-time constraints.
method Hybrid Matrix Decomposition (HMD) splits weight matrix into unconstrained and rank-1 blocks.
result HMD achieves 2-4x compression with faster run-time and similar accuracy.
Improved SVRG for quadratic functions achieves better performance and running times.
problem Minimizing quadratic functions with a specific type of Hessian matrix.
method Variant of SVRG algorithm for quadratic functions with improved analysis.
result Improved performance and running times for quadratic functions compared to state-of-the-art methods.
GANs improve anomaly detection in power plants, achieving nearly perfect classification.
problem Anomaly detection in power generation plants to identify irregularities.
method Used Generative Adversarial Networks (GANs) for anomaly detection in power generation plants.
result GANs achieved an accuracy rate of 98.99% in anomaly detection, significantly improved by data augmentation.
The rising popularity of intelligent mobile devices and the daunting computational cost of deep learning-based models call for efficient and accurate on-device inference schemes. We propose a quantization scheme that allows inference to be carried out using integer-only arithmetic, which can be implemented more efficie…
AITuning uses reinforcement learning to optimize communication libraries.
problem Optimizing communication libraries for better performance in parallel applications.
method Deep reinforcement learning applied to tuning communication libraries.
result Demonstrates the effectiveness of reinforcement learning for tuning communication libraries.
New method detects adversarial samples by constraining DNN behavior.
problem Adversarial samples fooling deep neural networks.
method Train DNN to enforce taboos for adversarial inputs.
result Detects adversarial samples causing taboo behaviors.
We study k-GenEV, the problem of finding the top k generalized eigenvectors, and k-CCA, the problem of finding the top k vectors in canonical-correlation analysis. We propose algorithms LazyEV and LazyCCA to solve the two problems with running times linearly dependent on the input size and…
This paper develops coding techniques to reduce the running time of distributed learning tasks. It characterizes the fundamental tradeoff to compute gradients (and more generally vector summations) in terms of three parameters: computation load, straggler tolerance and communication cost. It further gives an explicit c…
Efficient verified double auctions improve matching speed and detect errors.
problem Improving the efficiency and reliability of double auctions in financial markets.
method Formally verified implementation using Coq proof assistant, reducing time complexity and improving error detection.
result Improved efficiency with O(nlogn) time complexity, reducing runtime from days to minutes. Belief propagation and its variants are popular methods for approximate inference, but their running time and even their convergence depend greatly on the schedule used to send the messages. Recently, dynamic update schedules have been shown to converge much faster on hard networks than static schedules, namely the res…
Trojans can be inserted into deep neural networks without altering training data.
problem Inserting malicious code into deep learning models without changing training data.
method Patches model parameters in memory to achieve desired behavior on specific inputs.
result Efficient patches can induce trojan behavior with minimal risk of detection.
Long short-term memory (LSTM) has been widely used for sequential data modeling. Researchers have increased LSTM depth by stacking LSTM cells to improve performance. This incurs model redundancy, increases run-time delay, and makes the LSTMs more prone to overfitting. To address these problems, we propose a hidden-laye…
Randomly chosen support makes sparse linear regression easy.
problem Sparse linear regression with random support.
method Random support selection for efficient prediction.
result Prediction error ε with N=extpoly(k,logd,1/ε) samples and extpoly(d,N) run-time. New algorithm speeds up polynomial kernel approximations.
problem Efficiently approximating polynomial kernels of high degree.
method Oblivious sketching combined with novel sampling.
result Polynomial factor slowdown removed in running time.
Improved K-Means++ and K-Means∥ with faster run-time.
problem Efficiently selecting initial seeds for K-means clustering.
method Triangle inequality pruning and dynamic priority queue.
result Up to 17x speedup for K-Means++ and 551x for K-Means$\$.
We give the first algorithm for Matrix Completion whose running time and sample complexity is polynomial in the rank of the unknown target matrix, linear in the dimension of the matrix, and logarithmic in the condition number of the matrix. To the best of our knowledge, all previous algorithms either incurred a quadrat…
Efficiently learns complex Boolean functions under Gaussian distributions.
problem Learning complex Boolean functions of halfspaces under Gaussian marginals.
method First efficient proper agnostic learning algorithm for arbitrary Boolean functions of K halfspaces.
result Matches the best known improper learning algorithm's run-time dependence on dimension.
Software and hardware co-design and optimization of HPC systems has become intolerably complex, ad-hoc, time consuming and error prone due to enormous number of available design and optimization choices, complex interactions between all software and hardware components, and multiple strict requirements placed on perfor…
Quantum version of C5.0 algorithm improves decision tree construction time.
problem Improving the efficiency of decision tree construction in machine learning.
method Improved classical algorithm and applied quantum subroutines for faster decision tree construction.
result Quantum algorithm reduces decision tree construction time significantly.
Algorithms compute topological info about curves in surfaces.
problem Computing topological information about curves in surfaces.
method Algorithms using triangulations or handle structures to compute geometric intersection number and isotopy.
result Polynomial-time algorithms for topological curve analysis.
This work bounds the run-time of nonconvex optimization with early stopping.
problem Bounding the expected run-time of nonconvex optimization with early stopping.
method Derives conditions for well-defined early stopping based on validation function norms and bounds the expected number of iterations and gradient evaluations.
result Guarantees the validity of early stopping and provides bounds on the expected run-time for various optimization algorithms.
A new test statistic counts tree co-occurrences to detect edge correlation between networks.
problem Detecting edge correlation between networks using latent vertex correspondence.
method The test statistic is based on counting co-occurrences of signed trees for a family of non-isomorphic trees.
result The test runs in n2+o(1) time and succeeds with high probability for large n. We describe two techniques that significantly improve the running time of several standard machine-learning algorithms when data is sparse. The first technique is an algorithm that effeciently extracts one-way and two-way counts--either real or expected-- from discrete data. Extracting such counts is a fundamental step…
In this paper, we consider efficient differentially private empirical risk minimization from the viewpoint of optimization algorithms. For strongly convex and smooth objectives, we prove that gradient descent with output perturbation not only achieves nearly optimal utility, but also significantly improves the running …
We consider the structure learning problem for graphical models that we call loosely connected Markov random fields, in which the number of short paths between any pair of nodes is small, and present a new conditional independence test based algorithm for learning the underlying graph structure. The novel maximization …
We introduce dropout compaction, a novel method for training feed-forward neural networks which realizes the performance gains of training a large model with dropout regularization, yet extracts a compact neural network for run-time efficiency. In the proposed method, we introduce a sparsity-inducing prior on the per u…
Hybrid neural network infers states from black-box systems.
problem Inference of state models in black-box systems without source code instrumentation.
method Convolutional and recurrent layers learn correlations between time series signals.
result Improves state change point detection by up to 102%.
Paper compresses RNNs for resource-constrained devices.
problem Difficulty deploying RNNs on resource-constrained devices.
method Uses Kronecker product (KP) to compress RNN layers.
result KP compresses RNN layers by 16-38x with minimal accuracy loss.
New defense mechanism detects and mitigates poisoned regression data.
problem Vulnerability of regression models to targeted data poisoning attacks.
method Introduces N-LID, a measure of local intrinsic dimensionality to distinguish poisoned samples.
result N-LID based defense outperforms state-of-the-art methods in prediction accuracy and runtime.
In sparse recovery we are given a matrix A (the dictionary) and a vector of the form AX where X is sparse, and the goal is to recover X. This is a central notion in signal processing, statistics and machine learning. But in applications such as sparse coding, edge detection, compression and super resolution, t…
While matrix factorisation models are ubiquitous in large scale recommendation and search, real time application of such models requires inner product computations over an intractably large set of item factors. In this manuscript we present a novel framework that uses the inverted index representation to exploit struct…
Efficient decoder design improves semantic segmentation for real-time automated driving.
problem Efficient design of decoders for real-time semantic segmentation in automated driving.
method Design of a novel non-bottleneck layer and family of decoders using VGG10 as an efficient encoder.
result Improvement of 10% in performance compared to a baseline.