real-time data engineers

Abstract: Multi-label classification is particularly challenging in streaming scenarios, where data arrives sequentially. Online kernel methods offer a promising solution. However, prevailing methods rely on a single preselected kernel, making them prone to suboptimal choices since the global data distribution is unknown in advance in online settings. Although the recent method, Online Kernel Selection for Online Multi-label Classification (OKS-OMC), enables data-driven kernel selection, it fails to fully harness the complementary information from multiple kernels and encounters the curse of kernelization. To address these limitations, this paper introduces a novel online multi-kernel combination method for large-scale multi-label classification. First, an efficient and robust online single-kernel multi-label method is designed. Second, learning an optimal convex combination of multiple multi-label kernel classifiers is formalized as a structural risk minimization problem. An improved alternating optimization procedure is developed, in which the combination coefficients are updated by directly minimizing the objective function, while each kernel classifier is updated by minimizing a surrogate upper bound. This procedure decouples the learning of kernel classifiers from combination coefficients, allowing independent classifier updates via our single-kernel method and accelerating convergence to high-quality solutions. Our multi-kernel method is proven to asymptotically converge to the optimal fixed convex combination of the best fixed single-kernel models chosen in hindsight. Ablation studies confirm that our method's components outperform their counterparts in OKS-OMC. Comprehensive evaluations across 11 datasets and seven metrics demonstrate our method's overall superiority over existing online multi-label methods.

Abstract: Large language models (LLMs) have recently shown strong potential for time series reasoning, while models that reason over time series are usually with long chains of thought. However, this process often consumes thousands of tokens, directly leading to substantial latency during inference. In contrast, System 1 models such as Jev make decisions instantly and can naturally be an alternative, but raw time series are not compatible with the embedding space of these models, thus hindering the reasoning performance, especially when input series contain thousands of numeric points. In this paper, we make a very early attempt to propose a time series System 1 model, namely TimesJev. Specifically, we first formalize System 1 sufficiency in time series reasoning, which motivates a compressed representation for time series with key frequency patterns preserved. To construct this representation, we derive a dimension reduction objective that combines (i) a sufficiency divergence that measures the core information lost during compression, and (ii) a realizability divergence that quantifies the incompatibility of the System 1 model to the optimal prediction given this representation. We optimize this objective by learning time series compression with a gating mechanism for sufficiency, and then aligning the selected representation with the embedding space for realizability. Finally, experiments on 13 datasets demonstrate that TimesJev outperforms reasoning models by over 62% with 62.9% less inference time than their fine-tuned versions on average.

Abstract: Cox processes provide a principled Bayesian nonparametric framework for modeling event-based data through an underlying intensity function. However, existing inference methods for estimating the intensity typically rely on computationally expensive Markov chain Monte Carlo sampling or approximate inference techniques. In addition, to ensure tractability, these methods often define priors over indirect latent structures, making them challenging to interpret. In this paper, we introduce the Martingale Posterior Cox Process (MPCP), which recasts Bayesian intensity estimation as inference over unobserved events given the observed event history. This perspective avoids the need to define complex priors while retaining the flexibility of nonparametric modeling. We propose a scalable, GPU-friendly copula-based predictive update, and provide strong theoretical guarantees for the convergence of the predictive resampling algorithm. Empirically, we show that MPCP provides excellent performance in both simulations and real data at a fraction of the computational cost of competing Bayesian approaches.

Abstract: In random order online sorting, a fixed multiset of $n$ real numbers arrives in a uniformly random order. Each value must be placed immediately and irrevocably into an empty position of an array with exactly $n$ positions. The objective is to minimize the sum of the absolute differences between consecutive entries. If the entire input were known in advance, sorting the values would be optimal and would have cost equal to the range of the input. We prove that the optimal worst case competitive ratio in this model is $Θ(\log n)$ with high probability. In particular, we give a single online algorithm that achieves an $O(\log n)$ competitive ratio with high probability for every fixed input, and we show that every randomized online algorithm has some fixed input on which an $Ω(\log n)$ ratio is unavoidable with high probability. The same upper bound also holds for independent samples from an arbitrary unknown distribution on the real line. The algorithm uses the random arrival order to learn the relative positions of future values from the values seen so far. It maintains a hierarchy of small regions of the input order and allows an arriving value to use nearby space when its preferred region is full. This flexibility avoids the need to reserve large amounts of space for unlikely local fluctuations. The analysis shows that large displacements become rapidly less likely as their scale grows, leading to the $O(\log n)$ high probability bound. A matching lower bound shows that no randomized online algorithm can improve the logarithmic dependence in the worst case.

Abstract: Accurate workload forecasting is critical for elastic resource provisioning in web-scale cloud services, where distribution shifts driven by viral content, product launches, and user behavior degrade offline-trained models rapidly. Naive online learning recovers accuracy but incurs prohibitive per-step compute cost. We propose AdaptLSTM, an adaptive online framework that detects drift via validation-calibrated thresholds and applies selective, targeted updates. On the Alibaba Machine Trace, AdaptLSTM recovers 54\% of Naive Online's improvement at 20\% cost ($2.7\times$ efficiency, $p=0.002$ over 10 seeds). On the more volatile Container Trace, it achieves 96\% at 20\% cost ($4.8\times$ efficiency, $+75\%$ MAE reduction over Static). Unlike classical drift detectors (ADWIN, DDM, Page-Hinkley) which fail to trigger on regression-scale error streams, AdaptLSTM fires 42 times over 301 steps and outperforms matched-budget baselines. Wall-clock profiling shows $1.33\times$ throughput gain and 45\% update-time reduction. The framework is model-agnostic: identical Pareto patterns hold for LSTM, GRU, and Transformer backbones.