More Like this

1. Millimeter Wave and Free-Space-Optics for Future Dual-Connectivity 6DOF Mobile Multi-User VR Streaming

   https://doi.org/10.1145/3544494  

   Chakareski, Jacob ; Khan, Mahmudur ; Ropitault, Tanguy ; Blandino, Steve ( June 2022 , ACM Transactions on Multimedia Computing, Communications, and Applications)

   Dual-connectivity streaming is a key enabler of next generation six Degrees Of Freedom (6DOF) Virtual Reality (VR) scene immersion. Indeed, using conventional sub-6 GHz WiFi only allows to reliably stream a low-quality baseline representation of the VR content, while emerging high-frequency communication technologies allow to stream in parallel a high-quality user viewport-specific enhancement representation that synergistically integrates with the baseline representation, to deliver high-quality VR immersion. We investigate holistically as part of an entire future VR streaming system two such candidate emerging technologies, Free Space Optics (FSO) and millimeter-Wave (mmWave) that benefit from a large available spectrum to deliver unprecedented data rates. We analytically characterize the key components of the envisioned dual-connectivity 6DOF VR streaming system that integrates in addition edge computing and scalable 360° video tiling, and we formulate an optimization problem to maximize the immersion fidelity delivered by the system, given the WiFi and mmWave/FSO link rates, and the computing capabilities of the edge server and the users’ VR headsets. This optimization problem is mixed integer programming of high complexity and we formulate a geometric programming framework to compute the optimal solution at low complexity. We carry out simulation experiments to assess the performance of the proposed systemmore »using actual 6DOF navigation traces from multiple mobile VR users that we collected. Our results demonstrate that our system considerably advances the traditional state-of-the-art and enables streaming of 8K-120 frames-per-second (fps) 6DOF content at high fidelity.« less
2. HBMax: Optimizing Memory Efficiency for Parallel Influence Maximization on Multicore Architectures

   Chen, Xinyu ; Minutoli, Marco ; Tian, Jiannan ; Halappanavar, Mahantesh ; Kalyanaraman, Ananth ; Tao, Dingwen ( October 2022 , The 31st International Conference on Parallel Architectures and Compilation Techniques (PACT 2022))

   Influence maximization aims to select 𝑘 most-influential vertices or seeds in a network, where influence is defined by a given diffusion process. Although computing optimal seed set is NP-Hard, efficient approximation algorithms exist. However, even state-ofthe-art parallel implementations are limited by a sampling step that incurs large memory footprints. This in turn limits the problem size reach and approximation quality. In this work, we study the memory footprint of the sampling process collecting reverse reachability information in the IMM (Influence Maximization via Martingales) algorithm over large real-world social networks. We present a memory-efficient optimization approach (called HBMax) based on Ripples, a state-of-the-art multi-threaded parallel influence maximization solution. Our approach, HBMax, uses a portion of the reverse reachable (RR) sets collected by the algorithm to learn the characteristics of the graph. Then, it compresses the intermediate reverse reachability information with Huffman coding or bitmap coding, and queries on the partially decoded data, or directly on the compressed data to preserve the memory savings obtained through compression. Considering a NUMA architecture, we scale up our solution on 64 CPU cores and reduce the memory footprint by up to 82.1% with average 6.3% speedup (encoding overhead is offset by performance gain from memorymore »reduction) without loss of accuracy. For the largest tested graph Twitter7 (with 1.4 billion edges), HBMax achieves 5.9× compression ratio and 2.2× speedup.« less
3. Issues in the Reproducibility of Deep Learning Results

   https://doi.org/10.1109/SPMB47826.2019.9037840  

   Jean-Paul, S. ; Elseify, T. ; Obeid, I. ; Picone, J. ( December 2019 , IEEE Signal Processing in Medicine and Biology Symposium (SPMB))

   Obeid, I. ; Selesnik, I. ; Picone, J. (Ed.)

   The Neuronix high-performance computing cluster allows us to conduct extensive machine learning experiments on big data [1]. This heterogeneous cluster uses innovative scheduling technology, Slurm [2], that manages a network of CPUs and graphics processing units (GPUs). The GPU farm consists of a variety of processors ranging from low-end consumer grade devices such as the Nvidia GTX 970 to higher-end devices such as the GeForce RTX 2080. These GPUs are essential to our research since they allow extremely compute-intensive deep learning tasks to be executed on massive data resources such as the TUH EEG Corpus [2]. We use TensorFlow [3] as the core machine learning library for our deep learning systems, and routinely employ multiple GPUs to accelerate the training process. Reproducible results are essential to machine learning research. Reproducibility in this context means the ability to replicate an existing experiment – performance metrics such as error rates should be identical and floating-point calculations should match closely. Three examples of ways we typically expect an experiment to be replicable are: (1) The same job run on the same processor should produce the same results each time it is run. (2) A job run on a CPU and GPU should producemore »identical results. (3) A job should produce comparable results if the data is presented in a different order. System optimization requires an ability to directly compare error rates for algorithms evaluated under comparable operating conditions. However, it is a difficult task to exactly reproduce the results for large, complex deep learning systems that often require more than a trillion calculations per experiment [5]. This is a fairly well-known issue and one we will explore in this poster. Researchers must be able to replicate results on a specific data set to establish the integrity of an implementation. They can then use that implementation as a baseline for comparison purposes. A lack of reproducibility makes it very difficult to debug algorithms and validate changes to the system. Equally important, since many results in deep learning research are dependent on the order in which the system is exposed to the data, the specific processors used, and even the order in which those processors are accessed, it becomes a challenging problem to compare two algorithms since each system must be individually optimized for a specific data set or processor. This is extremely time-consuming for algorithm research in which a single run often taxes a computing environment to its limits. Well-known techniques such as cross-validation [5,6] can be used to mitigate these effects, but this is also computationally expensive. These issues are further compounded by the fact that most deep learning algorithms are susceptible to the way computational noise propagates through the system. GPUs are particularly notorious for this because, in a clustered environment, it becomes more difficult to control which processors are used at various points in time. Another equally frustrating issue is that upgrades to the deep learning package, such as the transition from TensorFlow v1.9 to v1.13, can also result in large fluctuations in error rates when re-running the same experiment. Since TensorFlow is constantly updating functions to support GPU use, maintaining an historical archive of experimental results that can be used to calibrate algorithm research is quite a challenge. This makes it very difficult to optimize the system or select the best configurations. The overall impact of all of these issues described above is significant as error rates can fluctuate by as much as 25% due to these types of computational issues. Cross-validation is one technique used to mitigate this, but that is expensive since you need to do multiple runs over the data, which further taxes a computing infrastructure already running at max capacity. GPUs are preferred when training a large network since these systems train at least two orders of magnitude faster than CPUs [7]. Large-scale experiments are simply not feasible without using GPUs. However, there is a tradeoff to gain this performance. Since all our GPUs use the NVIDIA CUDA® Deep Neural Network library (cuDNN) [8], a GPU-accelerated library of primitives for deep neural networks, it adds an element of randomness into the experiment. When a GPU is used to train a network in TensorFlow, it automatically searches for a cuDNN implementation. NVIDIA’s cuDNN implementation provides algorithms that increase the performance and help the model train quicker, but they are non-deterministic algorithms [9,10]. Since our networks have many complex layers, there is no easy way to avoid this randomness. Instead of comparing each epoch, we compare the average performance of the experiment because it gives us a hint of how our model is performing per experiment, and if the changes we make are efficient. In this poster, we will discuss a variety of issues related to reproducibility and introduce ways we mitigate these effects. For example, TensorFlow uses a random number generator (RNG) which is not seeded by default. TensorFlow determines the initialization point and how certain functions execute using the RNG. The solution for this is seeding all the necessary components before training the model. This forces TensorFlow to use the same initialization point and sets how certain layers work (e.g., dropout layers). However, seeding all the RNGs will not guarantee a controlled experiment. Other variables can affect the outcome of the experiment such as training using GPUs, allowing multi-threading on CPUs, using certain layers, etc. To mitigate our problems with reproducibility, we first make sure that the data is processed in the same order during training. Therefore, we save the data from the last experiment and to make sure the newer experiment follows the same order. If we allow the data to be shuffled, it can affect the performance due to how the model was exposed to the data. We also specify the float data type to be 32-bit since Python defaults to 64-bit. We try to avoid using 64-bit precision because the numbers produced by a GPU can vary significantly depending on the GPU architecture [11-13]. Controlling precision somewhat reduces differences due to computational noise even though technically it increases the amount of computational noise. We are currently developing more advanced techniques for preserving the efficiency of our training process while also maintaining the ability to reproduce models. In our poster presentation we will demonstrate these issues using some novel visualization tools, present several examples of the extent to which these issues influence research results on electroencephalography (EEG) and digital pathology experiments and introduce new ways to manage such computational issues.« less
4. OMGS: Optical Map-based Genome Scaffolding

   https://doi.org/10.1007/978-3-030-17083-7_12  

   W. Pan, T. Jiang ( January 2019 , RECOMB 2019 - ACM Annual Conference on Research in Computational Molecular Biology)

   Due to the current limitations of sequencing technologies, de novo genome assembly is typically carried out in two stages, namely contig (sequence) assembly and scaffolding. While scaffolding is computationally easier than sequence assembly, the scaffolding problem can be challenging due to the high repetitive content of eukaryotic genomes, possible mis-joins in assembled contigs and inaccuracies in the linkage information. Genome scaffolding tools either use paired-end/mate-pair/linked/Hi-C reads or genome-wide maps (optical, physical or genetic) as linkage information. Optical maps (in particular Bionano Genomics maps) have been extensively used in many recent large-scale genome assembly projects (e.g., goat, apple, barley, maize, quinoa, sea bass, among others). However, the most commonly used scaffolding tools have a serious limitation: they can only deal with one optical map at a time, forcing users to alternate or iterate over multiple maps. In this paper, we introduce a novel scaffolding algorithm called OMGS that for the first time can take advantages of multiple optical maps. OMGS solves several optimization problems to generate scaffolds with optimal contiguity and correctness. Extensive experimental results demonstrate that our tool outperforms existing methods when multiple optical maps are available, and produces comparable scaffolds using a single optical map. OMGS can be obtainedmore »from GIT.« less
5. An Innovative Formulation Tightening Approach for Job-Shop Scheduling

   https://doi.org/10.1109/TASE.2021.3088047  

   Yan, Bing ; Bragin, Mikhail A. ; Luh, Peter B. ( June 2021 , IEEE Transactions on Automation Science and Engineering)

   Job shops are an important production environment for low-volume high-variety manufacturing. Its scheduling has recently been formulated as an Integer Linear Programming (ILP) problem to take advantages of popular Mixed-Integer Linear Programming (MILP) methods, e.g., branch-and-cut. When considering a large number of parts, MILP methods may combinatorial difficulties. To address this, a critical but much overlooked issue is formulation tightening. The idea is that if problem constraints can be transformed to directly delineate the problem convex hull in the data preprocessing stage, then a solution can be obtained by using linear programming methods without combinatorial difficulties. The tightening process, however, is fundamentally challenging because of the existence of integer variables. In this paper, an innovative and systematic approach is established for the first time to tighten the formulations of individual parts, each with multiple operations, in the data preprocessing stage. It is a major advancement of our previous work on problems with binary and continuous variables to integer variables. The idea is to first link integer variables to binary variables by innovatively combining constraints so that the integer variables are uniquely determined by the binary variables. With binary and continuous variables only, it is proved that the vertices of themore »convex hull can be obtained based on vertices of the linear problem after relaxing binary requirements. These vertices are then converted to tightened constraints for general use. This approach significantly improves our previous results on tightening individual operations. Numerical results demonstrate significant benefits on solution quality and computational efficiency. This approach also applies to other ILP problems with similar characteristics and fundamentally changes the way how such problems are formulated and solved.« less