Tcm: A High-Precision Lossy Compression Algorithm for Time Series Data With Flexible Queue-Value Dynamic Grouping

Two Stage Decomposition with Hybrid BiLSTM-BiGRU Networks for Accurate and Efficient Data Center Workload Prediction

Accurate workload prediction in cloud data centers is essential for efficient resource management, yet high-dimensional and noisy operational data often hinder forecasting performance. This work extends the original CVCBM model by integrating a lightweight Bidirectional GRU (BiGRU) with Bidirectional LSTM (BiLSTM) to enhance prediction efficiency while maintaining temporal feature extraction. Initially, workload signals are denoised and decomposed using a two-stage process—Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) followed by Variational Mode Decomposition (VMD). Sample Entropy (SE) selects meaningful components, and K-Means clustering prioritizes high workload data for training. The hybrid Conv1D-BiLSTM-BiGRU architecture captures multi-scale temporal patterns and both short-term and long-term dependencies. The trained model is deployed using the Flask framework for real-time workload prediction, allowing interactive input of datasets and immediate forecasting. Experimental evaluation demonstrates that the extended model reduces computational overhead while improving prediction accuracy, providing robust, scalable, and real-time forecasting for cloud data center resource management.

Deep Neural Network Compression via Data-Driven Low-Rank Singular Value Decomposition

This paper proposes a novel compression method that uses Singular Value Decomposition (SVD) informed by data examples that achieves substantial reductions in model size and computation with minimal impact on accuracy and demonstrates its applicability in compressing deep neural networks to a fraction of their original size.

FTCG: Fine-to-Coarse Multi-Granularity Grouping for Migratory Compression

EvtGraph: Event-Adaptive Compression for Sparse Temporal Graph Learning in Multimodal Time Series

Multimodal temporal data are inherently irregular and uneven in information density, yet most models rely on uniform discretization, leading to inefficient representations. We propose \textbf{EvtGraph}, a unified framework that aligns computation with temporal salience under explicit budget constraints. EvtGraph reparameterizes sequences into event-level tokens via event-adaptive compression (EAMC), selects a compact subset with a node budget (NBC), and performs temporally constrained sparse graph reasoning (T2SG). This transforms dense sequences into structured computation over salient events, reducing complexity while preserving critical transitions. We show that this design provides a practical mechanism for allocating representational capacity under a fixed budget, yielding a consistent performance--efficiency trade-off, where a small budget is often sufficient in practice. Experiments on multimodal clinical (MIMIC-IV + CXR) and cross-domain benchmarks demonstrate that EvtGraph outperforms both Transformer-based and recurrent baselines while significantly improving efficiency. These results suggest that budget-constrained event-centric representation provides a general paradigm for learning from high-redundancy temporal data.

Fast and Scalable Caputo Fractional Gradient Descent via Perturbation-Preserving Memory Compression

Fractional gradient descent (FGD) incorporates long-range memory through Caputo-type operators and has been shown to improve stability in ill-conditioned and nonconvex optimization problems. Despite these advantages, its practical use remains limited, mainly due to the high computational cost of evaluating history-dependent convolutions, which scales quadratically with the number of iterations. In this paper, we focus on making Caputo-based optimization computationally viable without sacrificing its intrinsic memory structure. We begin by expressing the fractional descent direction as a discrete convolution over past gradients, which provides a unified view of the method. Based on this formulation, we introduce two complementary mechanisms to reduce the cost of the memory term. The first uses a sum-of-exponentials (SOE) approximation of the power-law kernel, leading to efficient recursive updates. The second approach, newly proposed in this paper as dyadic hierarchical discrete convolution (DHDC), compresses the gradient history through a multiscale aggregation strategy. Rather than treating these approximations as purely numerical accelerations, we interpret them as perturbations of the ideal Caputo operator. This viewpoint allows us to analyze how the compressed memory affects the optimization dynamics. Under standard $\mu$-strong convexity and $L$-smoothness assumptions, we show that the resulting method still exhibits monotone descent and linear convergence, provided that the approximation error remains controlled.

Fast and Memory-Efficient Wavelet Convolutions via I/O-Aware Reformulation

Wavelet convolution (WTConv) has emerged as an increasingly popular drop-in replacement for standard convolutions, expanding a network's receptive field exponentially with the number of decomposition levels while keeping the parameter count linear. However, its reference implementation is severely memory-bound due to excessive data movement through high-bandwidth memory (HBM). We develop an I/O model of WTConv to characterize this bottleneck and use it to guide three algebraic reformulations: (1) recomputing the inexpensive Haar analysis butterfly on chip, (2) collapsing the multi-level synthesis cascade into a single closed-form pass indexed by output-coordinate bits, and (3) folding learned per-channel scales into the convolution weights. Together, these reformulations enable an I/O-aware fused implementation that substantially reduces HBM traffic. We evaluate the WTConvNeXt configuration across decomposition levels and a broad range of tensor shapes. Despite performing comparable arithmetic, the reference WTConv is substantially slower than the depthwise convolution it replaces. Our reformulation reduces modeled HBM traffic by approximately $2.55\times$, yielding up to a $4.35\times$ training speedup over the reference while roughly halving peak memory usage. Thus, our reformulation preserves the benefits of WTConv while substantially reducing its execution time and memory footprint, removing the systems overhead that previously limited its practical efficiency.