We present an approach for implementing a formally certified loop-invariantcode motion optimization by composing an unrolling pass and an efficient global subexpression elimination . Each pass comes with a simple and independent proof ofcorrectness . The approach significantly narrows the performance gap between the CompCert certified compiler and state-of-the-art optimizingcompilers .…
The Role of Time and Data Online Conformance Checking in the Manufacturing Domain
Manufacturing is a challenging domain that craves for process-oriented technologies to address digitalization challenges . Process mining creates high expectations, but its implementation and usage of it is unclear to a certain extent . The findings emphasize the importance of online conformance checking inmanufacturing and show how appropriate data sets can be identified andgenerated .…
Automatic Learning to Detect Concept Drift
Active Drift Detection with Meta learning (Meta-ADD) is a novel framework that learns to classify concept drift by tracking the changed pattern of error rates . Meta-ADD uses machine learning to learn to detect concept drifts and identify their types automatically, which candirectly support drift understand .…
An Overview of Laser Injection against Embedded Neural Network Models
The deployment of models in a large variety of devices faces several obstacles related to trust and security . Fault Injection Analysis (FIA) are known to be very powerful with a large spectrum of attack vectors . Laser injection with state-of-the-art equipment, combined with theoretical evidences from Adversarial Machine Learning, highlights worryingthreats against the integrity of deep learning inference and claims that joinefforts from the theoretical AI and Physical Security communities are a urgent need .…
An Empirical Review of Deep Learning Frameworks for Change Detection Model Design Experimental Frameworks Challenges and Research Needs
Visual change detection is one of the elementary tasks in computervision and video analytics . Applications include anomaly detection, object tracking, traffic monitoring, human machine interaction, behavior analysis, action recognition, and visual surveillance . The challenges in change detection include background fluctuations,illumination variation, weather changes, intermittent object motion, shadow, camera motion, and heterogeneous object shapes .…
Dual Cross Central Difference Network for Face Anti Spoofing
Face anti-spoofing (FAS) plays a vital role in securing face recognitionsystems . Central difference convolution (CDC) has shown its excellent capacity for the FAS task via leveraging local gradientfeatures . However, aggregating central difference clues from allneighbors/directions simultaneously makes CDC redundant and sub-optimized .…
LAFFNet A Lightweight Adaptive Feature Fusion Network for Underwater Image Enhancement
There are many deep-learning-based methods with impressive performance for underwater image enhancement, but their memory and model parameter costs are hindrances in practical application . Toaddress this issue, we propose a lightweight adaptive feature fusion network(LAFFNet) The model is the encoder-decoder model with multiple adaptivefeature fusion (AAF) modules .…
Technical Report for Valence Arousal Estimation on Affwild2 Dataset
In this work, we describe our method for tackling the valence-arousalestimation challenge from ABAW FG-2020 Competition . The competition organizers provide an in-the-wild Aff-Wild2 dataset for participants to analyze affectivebehavior in real-life settings . We use MIMAMO Net to achieve information about micro-motion and macro-motion for improving videoemotion recognition .…
Collaborative Multi Resource Allocation in Terrestrial Satellite Network Towards 6G
Terrestrial-satellite networks are envisioned to play a significant role inthe sixth-generation (6G) wireless networks . In such networks, hot air balloons are useful as they can relay the signals between satellites and groundstations . Most existing works assume the same height with the same minimum elevation angle to the satellites, which may not be practical due to possible route conflict with airplanes and otherflight equipment .…
Canonical Saliency Maps Decoding Deep Face Models
The Canonical Saliency Maps highlight facial features responsible for the decision made by a deep face model on a given image . Image-level maps highlight facialfeatures responsible for a DNN decision, thus helping to understand how a . DNN made a prediction on the image .…
Weak Multi View Supervision for Surface Mapping Estimation
We propose a weakly-supervised multi-view learning approach to learn category-specific surface mapping without dense annotations . We learn theunderlying surface geometry of common categories, such as human faces, cars,and airplanes, given instances from those categories . Our approach leverages information from multiple views of the object to establish additional consistency cycles, thus improving surface mapping understanding .…
Federated Multi View Learning for Private Medical Data Integration and Analysis
Medical data is naturally distributed across multiple sites, making it difficult to collectively train machine learning models without data leakage . In medical applications, data are oftencollected from different sources and views, resulting in heterogeneity and complexity that requires reconciliation .…
Hallucination Improves Few Shot Object Detection
Learning to detect novel objects from few annotated examples is of greatpractical importance . A particularly challenging yet common regime occurs whenthere are extremely limited examples (less than three) One critical factor in improving few-shot detection is to address the lack of variation in training data .…
YAPS Your Open Examination System for Activating and emPowering Students
There are numerous e-assessment systems devoted to specific domains underdiverse license models . Cost, extensibility, and maintainability are relevant issues for an institution . Ease of use and inclusion into courses are main concerns . For students the user experience and fast transparent feedback plus “better” tests are most important .…
Defeating Super Reactive Jammers With Deception Strategy Modeling Signal Detection and Performance Analysis
This paper develops a novel framework to defeat a super-reactive jammer, one of the most difficult jamming attacks to deal with in practice . We introduce a smart deception mechanism to attract the jammer to continuously attack the channel and then leverage jamming signalsto transmit data based on the ambient backscatter communication technology .…
Self Supervised Approach for Facial Movement Based Optical Flow
Deep learning-based optical flow techniques do not perform well for non-rigidmovements such as those found in faces . We hypothesize that learning opticalflow on face motion data will improve the quality of predicted flow on faces . The performance of FlowNetS trained on face images surpassed that of other opticalflow CNN architectures, demonstrating its usefulness.…
Counting vertices of integer polytopes defined by facets
We present a number of complexity results concerning the problem of counting vertices of an integral polytope . The focus is on polytopes with small integer vertices, particularly 0/1polytopes .…
Online Transfer Learning Negative Transfer and Effect of Prior Knowledge
Transfer learning is a machine learning paradigm where the knowledge from onetask is utilized to resolve the problem in a related task . In this paper, we study the online transfer learning problems where the sourcesamples are given in an offline way while the target samples arrive .…
Data Efficient Reinforcement Learning for Malaria Control
The main challenge faced by policymakers is to learn a policy from scratch by interacting with a complex environment in a few trials . This work introduces apractical, data-efficient policy learning method, named Variance-Bonus MonteCarlo Tree Search~(VB-MCTS) It can copy with very little data andfacilitate learning from scratch in only a few trial times .…
Effects of Quantization on the Multiple Round Secret Key Capacity
We consider the strong secret key (SK) agreement problem for the satellitecommunication setting . Legitimate receivers have access to an authenticated, noiseless, two-way, and public communication link . The noise variances for Alice’s and Bob’s measurement channels are both fixed to a value $Q1$, whereas the noise over Eve’s measurement channel has a unitvariance, so $Q$ represents a channel quality ratio .…
Continuous indetermination and average likelihood minimization
Authors transpose a discrete notion of indetermination coupling in thecase of continuous probabilities . They show that this coupling, expressed ondensities, cannot be captured by a specific copula which acts on cumulativedistribution functions without a high dependence on the margins .…
Autonomous Robotic Mapping of Fragile Geologic Features
Robotic mapping is useful in scientific applications that involve surveyingunstructured environments . This paper presents a target-oriented mapping system for sparsely distributed geologic surface features, such as precariouslybalanced rocks (PBRs), whose geometric fragility parameters can provide valuable information on earthquake shaking history and landscape development .…
Walk in the Cloud Learning Curves for Point Clouds Shape Analysis
Discrete point cloud objects lack sufficient shape descriptors of 3Dgeometries . In this paper, we present a novel method for aggregatinghypothetical curves in point clouds . Sequences of connected points (curves) areinitially grouped by taking guided walks in the point clouds, and then aggregated back to augment their point-wise features .…
The Pursuit of Knowledge Discovering and Localizing Novel Categories using Dual Memory
We tackle object category discovery, which is the problem of discovering andlocalizing novel objects in a large unlabeled dataset . We propose a method to use prior knowledge about certain object categories to discover new categories by leveraging twomemory modules, namely Working and Semantic memory .…
Eigenfactor
The Eigenfactor is a journal metric, which was developed by Bergstrom and his colleagues at the University of Washington . It establishes the importance, influence or impact of a journal based on its location in a network of journals . While journal-basedmetrics have been criticized, it has also been suggested as analternative in the widely used San Francisco Declaration on Research Assessment(DORA) The algorithm is based on Eigenvector centrality, i.e.…
QSOC Quantum Service Oriented Computing
Quantum computing is quickly turning from a promise to a reality, witnessing the launch of several cloud-based, general-purpose offerings, and IDEs . Quantum Service-Oriented Computing (QSOC) is a model-driven methodology to allow DevOps teams to compose, configure and operate enterprise applications without intimate knowledge on the underlying quantuminfrastructure .…
MLP Mixer An all MLP Architecture for Vision
Convolutional Neural Networks (CNNs) are the go-to model for computer vision . Attention-based networks, such as the Vision Transformer, have also become popular . In this paper we show that while convolutions and attention are sufficient for good performance, neither of them are necessary .…
HASCO Towards Agile HArdware and Software CO design for Tensor Computation
Tensor computations overwhelm traditional general-purpose computing devices . They callfor a holistic solution composed of both hardware acceleration and softwaremapping . Hardware/software (HW/SW) co-design optimizes the hardware andsoftware in concert and produces high-quality solutions . Hasco achieves a 1.25X to 1.44Xlatency reduction through HW/SW co-Design compared with developing the hardwareand software separately .…
Riemannian Geometry with differentiable ambient space and metric operator
We show Riemannian geometry could be studied by identifying the tangentbundle of a Riemanian manifold with a subbundle . Given such an embedding, we can extend the metric tensor on $M$ to a (positive-definite) operator-valued function acting on $Euclidean space .…
Deep Reinforcement Learning for Adaptive Exploration of Unknown Environments
The proposed approach uses a map segmentation technique to decompose the environment map into smaller, tractable maps . A simple information gain function is computed to determine the best target region to search during eachiteration of the process . DDQN and A2C algorithms are extended with a stack ofLSTM layers and trained to generate optimal policies for the exploration andexploitation, respectively .…
Towards Accountability in the Use of Artificial Intelligence for Public Administrations
We argue that distributed responsibility, inducedacceptance, and acceptance through ignorance constitute instances of imperfectdelegation when tasks are delegated to computationally-driven systems . We hold that both directpublic accountability via public transparency and indirect publicaccountability via transparency to auditors in public organizations can be bothinstrumentally ethically valuable and required as a matter of deontology from the principle of democratic self-government .…
A Priori Generalization Error Analysis of Two Layer Neural Networks for Solving High Dimensional Schrödinger Eigenvalue Problems
This paper analyzes the generalization error of two-layer neural networks for computing the ground state of the Schr\”odinger operator on a $d$-dimensionalhypercube . We prove that the convergence rate of the error isindependent of the dimension $d$, under the a priori assumption that the groundstate lies in a spectral Barron space .…
Two Stage Facility Location Games with Strategic Clients and Facilities
We consider non-cooperative facility location games where both facilities and clients act strategically and heavily influence each other . This contrasts established game-theoretic facility location models with non-strategic clientsthat simply select the closest opened facility . We focus on a natural client behavior similar to classical loadbalancing: our selfish clients aim for a distribution that minimizes their maximum waiting times for getting serviced, where a facility’s waiting timecorresponds to its total attracted client weight .…
Deterministic Rounding of Dynamic Fractional Matchings
We present a framework for deterministically rounding a dynamic fractional matching algorithm . This is the first dynamic matching algorithm that works on general graphs by using an algorithm for low-arboricity graphs as ablack-box subroutine . Our rounding scheme works by maintaining a good {\em matching-sparsifier} with bounded arboricity, and then applying the algorithm of Peleg and Solomon[SODA’16] to maintain a near-optimal matching in this low arboric graph .…
Online adaptive basis construction for nonlinear model reduction through local error optimization
The accuracy of the reduced-order model (ROM) mainly depends on the selected basis . It is essential to compute an appropriate basis with anefficient numerical procedure when applying ROM to nonlinear problems . In the proposed method, the adaptive basis is defined by the low-rank updateformulation .…
A Guide for New Program Committee Members at Theoretical Computer Science Conferences
In theoretical computer science, conferences play an important role in the scientific process . The decisions whether to accept or reject articles is taken by the program committee (PC) members . This guide will help new program-committee members understand how the system works and provide useful tips and guidelines .…
Implicit differentiation for fast hyperparameter selection in non smooth convex learning
Finding the optimal hyperparameters of a model can be cast as a bileveloptimization problem, typically solved using zero-order techniques . In thiswork we study first-order methods when the inner optimization problem is convexbut non-smooth . We show that the forward-mode differentiation of proximal gradient descent and proximal coordinate descent yield sequences of Jacobiansconverging toward the exact Jacobian .…
Simulation by Rounds of Letter to Letter Transducers
Letter-to-letter transducers are a standard formalism for modeling reactivesystems . Often, two transducers that model similar systems differ locally fromone another, by behaving similarly, up to permutations of the input and outputletters within “rounds” In our setting,words are partitioned to consecutive subwords of a fixed length $k$ calledrounds .…
Learning 3D Granular Flow Simulations
Graph Neural Networks approach towards accurate modeling of complex 3D granular flow simulation processes . We discuss how to implement GraphNeural Networks that deal with 3D objects, boundary conditions, particle -particle, and particle – boundary interactions . We compare themachine learning based trajectories to LIGGGHTS trajectories in terms of particle flows and mixing entropies.…
Signal automata and hidden Markov models
A generic method for inferring a dynamical hidden Markov model from a timeseries is proposed . Under reasonable hypothesis, the model is updated inconstant time whenever a new measurement arrives .…
Moving Towards Centers Re ranking with Attention and Memory for Re identification
Re-ranking utilizes contextual information to optimize the initial rankinglist of person or vehicle re-identification (re-ID) This paper proposes a re-ranking networkto predict the correlations between the . probe and top-ranked neighbor samples . The process is equivalent to moving independent embeddings toward theidentity centers, improving cluster compactness .…
Multiparty Interactive Coding over Networks of Intersecting Broadcast Links
A simple variant of a coding scheme by Rajagopalan and Schulman (STOC 1994) shows that any (noiseless) protocol of $R$ rounds can be reliably simulated in $O(R\log n)$ rounds . We design interactive codingschemes that successfully perform any computation over these noisy networks .…
Towards security recommendations for public key infrastructures for production environments in the post quantum era
Quantum computing technologies pose a significant threat to the currently employed public-key cryptography protocols . We discuss the impact of the quantum threat on public key infrastructures (PKIs) We attempt to provide a set of securityrecommendations regarding the PKI from the viewpoints of attacks with quantumcomputers .…
Towards Error Measures which Influence a Learners Inductive Bias to the Ground Truth
New error measures are shown to create an unhelpful bias and a new errormeasure is derived which does not exhibit this behaviour . This is tested on 36representative data sets with different characteristics, showing that it is more consistent in determining the `ground truth’ and in giving improvedpredictions in regions beyond the range of the training data .…
Where and When Space Time Attention for Audio Visual Explanations
Recent advances in XAI provide explanations for models trained on still images . But when it comes to modeling multiplesensory modalities in a dynamic world, it remains underexplored how tomystify the mysterious dynamics of a complex multi-modal model . We propose a novel space-time attention network that uncovers the synergistic dynamics of audio and visual data overboth space and time .…
COVID Net CT S 3D Convolutional Neural Network Architectures for COVID 19 Severity Assessment using Chest CT Images
The health and socioeconomic difficulties caused by the COVID-19 pandemiccontinues to cause enormous tensions around the world . A critical step in the treatment andmanagement of COID-19 positive patients is severity assessment, which is challenging even for expert radiologists given the subtleties at differentstages of lung disease severity .…
Environment Modeling During Model Checking of Cyber Physical Systems
Modelchecking has been proposed for validation of Cyber-Physical Systems . Adomain-independent framework based on timed-automata is proposed forabstraction and refinement of environment models during model checking . The framework maintains an abstraction tree of environment model models, which provides counter-examples interpretable by experts in the application domain .…
Optimal Algorithms for Range Searching over Multi Armed Bandits
This paper studies a multi-armed bandit (MAB) version of the range-searching problem . In its basic form, range searching considers as input a set of points and a collection of (real) intervals . The current work addresses range searching with stochastic weights: eachpoint corresponds to an arm (that admits sample access) and the point’s weightis the (unknown) mean of the underlying distribution .…
Intersection Patterns in Optimal Binary 5 3 Doubling Subspace Codes
Subspace codes are collections of subspaces of a projective space that satisfy a pairwise minimum distance criterion . Recent resultshave shown that it is possible to construct optimal $(5,3)$ subspace codes frompairs of partial spreads in the projective . space over thefinite field $ \mathbb{F}_q $, termed doubling codes .…
Small Sample Inferred Adaptive Recoding for Batched Network Coding
Batched network coding is a low-complexity network coding solution tofeedbackless multi-hop wireless packet network transmission with packet loss . Adaptiverecoding is a technique to adapt the fluctuation of packet loss by optimizing the number of recoded packets per batch to enhance the throughput .…