Lithium-ion batteries (LIBs) are utilized as a major energy source in various fields because of their high energy density and long lifespan. During repeated charging and discharging, the degradation of LIBs, which reduces their maximum power output and operating time, is a pivotal issue. This degradation can affect not only battery performance but also safety of the system. Therefore, it is essential to accurately estimate the state-of-health (SOH) of the battery in real time. To address this problem, we propose a fast SOH estimation method that utilizes the sparse model identification algorithm (SINDy) for nonlinear dynamics. SINDy can discover the governing equations of target systems with low data assuming that few functions have the dominant characteristic of the system. To decide the state of degradation model, correlation analysis is suggested. Using SINDy and correlation analysis, we can obtain the data-driven SOH model to improve the interpretability of the system. To validate the feasibility of the proposed method, the estimation performance of the SOH and the computation time are evaluated by comparing it with various machine learning algorithms.

Bayesian optimization relies on iteratively constructing and optimizing an acquisition function. The latter turns out to be a challenging, non-convex optimization problem itself. Despite the relative importance of this step, most algorithms employ sampling- or gradient-based methods, which do not provably converge to global optima. This work investigates mixed-integer programming (MIP) as a paradigm for \textit{global} acquisition function optimization. Specifically, our Piecewise-linear Kernel Mixed Integer Quadratic Programming (PK-MIQP) formulation introduces a piecewise-linear approximation for Gaussian process kernels and admits a corresponding MIQP representation for acquisition functions. We analyze the theoretical regret bounds of the proposed approximation, and empirically demonstrate the framework on synthetic functions, constrained benchmarks, and a hyperparameter tuning task.

Telephone spam has been among the highest network security concerns for users for many years. In response, industry and government have deployed new technologies and regulations to curb the problem, and academic and industry researchers have provided methods and measurements to characterize robocalls. Have these efforts borne fruit? Are the research characterizations reliable, and have the prevention and deterrence mechanisms succeeded? In this paper, we address these questions through analysis of data from several independently-operated vantage points, ranging from industry and academic voice honeypots to public enforcement and consumer complaints, some with over 5 years of historic data. We first describe how we address the non-trivial methodological challenges of comparing disparate data sources, including comparing audio and transcripts from about 3 million voice calls. We also detail the substantial coherency of these diverse perspectives, which dramatically strengthens the evidence for the conclusions we draw about robocall characterization and mitigation while highlighting advantages of each approach. Among our many findings, we find that unsolicited calls are in slow decline, though complaints and call volumes remain high. We also find that robocallers have managed to adapt to STIR/SHAKEN, a mandatory call authentication scheme. In total, our findings highlight the most promising directions for future efforts to characterize and stop telephone spam.

Stochastic gradient descent with momentum is a popular variant of stochastic gradient descent, which has recently been reported to have a close relationship with the underdamped Langevin diffusion. In this paper, we establish a quantitative error estimate between them in the 1-Wasserstein and total variation distances.

We used off-the-shelf interpretable ML techniques to combine information from multiple heterogeneous spectra: X-ray absorption near-edge spectra (XANES) and atomic pair distribution functions (PDFs), to extract information about local structure and chemistry of transition metal oxides. This approach enabled us to analyze the relative contributions of the different spectra to different prediction tasks. Specifically, we trained random forest models on XANES, PDF, and both of them combined, to extract charge (oxidation) state, coordination number, and mean nearest-neighbor bond length of transition metal cations in oxides. We find that XANES-only models tend to outperform the PDF-only models for all the tasks, and information from XANES often dominated when the two inputs were combined. This was even true for structural tasks where we might expect PDF to dominate. However, the performance gap closes when we used species-specific differential PDFs (dPDFs) as the inputs instead of total PDFs. Our results highlight that XANES contains rich structural information and may be further developed as a structural probe. Our interpretable, multimodal approach is quick and easy to implement when suitable structural and spectroscopic databases are available. This approach provides valuable insights into the relative strengths of different modalities for a practical scientific goal, guiding researchers in their experiment design tasks such as deciding when it is useful to combine complementary techniques in a scientific investigation.

Curating a desirable dataset for training has been the core of building highly capable large language models (Touvron et al., 2023; Achiam et al., 2023; Team et al., 2024). Gradient influence scores (Pruthi et al., 2020; Xia et al., 2024) are shown to be correlated with model performance and are commonly used as the criterion for data selection. However, existing methods are built upon either individual sample rankings or inefficient matching process, leading to suboptimal performance or scaling up issues. In this paper, we propose Gradient Trajectory Pursuit (GTP), an algorithm that performs pursuit of gradient trajectories via jointly selecting data points under an L0-norm regularized objective. The proposed algorithm highlights: (1) joint selection instead of independent top-k selection, which automatically de-duplicates samples; (2) higher efficiency with compressive sampling processes, which can be further sped up using a distributed framework. In the experiments, we demonstrate the algorithm in both in-domain and target-domain selection benchmarks and show that it outperforms top-k selection and competitive algorithms consistently, for example, our algorithm chooses as low as 0.5% data to achieve full performance on the targeted instruction tuning tasks. Large language models encompasses an enormous amount of knowledge acquired through pretraining corpus (Brown et al., 2020; Jiang et al., 2023; Touvron et al., 2023). A crucial component that makes language models practically useful is the post-training phase, which empower the model with a variety of extra abilities and skills, such as aligning language models to follow human instructions (Ouyang et al., 2022; Taori et al., 2023; Wang et al., 2023b; Xu et al., 2023), teaching models the tool use (Schick et al., 2023) or exploring environments (Carta et al., 2023; Lin et al., 2023).

We study two strange phenomena in auto-regressive Transformers: (1) the dominance of the first token in attention heads; (2) the occurrence of large outlier activations in the hidden states. We find that popular large language models, such as Llama attend maximally to the first token in 98% of attention heads, a behaviour we attribute to the softmax function. To mitigate this issue, we propose a reformulation of softmax to softmax-1. Furthermore, we identify adaptive optimisers, e.g. Adam, as the primary contributor to the large outlier activations and introduce OrthoAdam, a novel optimiser that utilises orthogonal matrices to transform gradients, to address this issue. Finally, not only do our methods prevent these phenomena from occurring, but additionally, they enable Transformers to sustain their performance when quantised using basic algorithms, something that standard methods are unable to do. In summary, our methods reduce the attention proportion on the first token from 65% to 3.3%, the activation kurtosis in the hidden states from 1657 to 3.1, and perplexity penalty under 4-bit weight quantisation from 3565 to 0.3.

Algorithmic robust statistics has traditionally focused on the contamination model where a small fraction of the samples are arbitrarily corrupted. We consider a recent contamination model that combines two kinds of corruptions: (i) small fraction of arbitrary outliers, as in classical robust statistics, and (ii) local perturbations, where samples may undergo bounded shifts on average. While each noise model is well understood individually, the combined contamination model poses new algorithmic challenges, with only partial results known. Existing efficient algorithms are limited in two ways: (i) they work only for a weak notion of local perturbations, and (ii) they obtain suboptimal error for isotropic subgaussian distributions (among others). The latter limitation led [NGS24, COLT'24] to hypothesize that improving the error might, in fact, be computationally hard. Perhaps surprisingly, we show that information theoretically optimal error can indeed be achieved in polynomial time, under an even \emph{stronger} local perturbation model (the sliced-Wasserstein metric as opposed to the Wasserstein metric). Notably, our analysis reveals that the entire family of stability-based robust mean estimators continues to work optimally in a black-box manner for the combined contamination model. This generalization is particularly useful in real-world scenarios where the specific form of data corruption is not known in advance. We also present efficient algorithms for distribution learning and principal component analysis in the combined contamination model.

The 2008 financial crisis that hit the world's economies has had a particularly acute impact in Spain (Guardiola and Guillen-Royo, 2015). It is only since 2014 that Spain seemed to begin its recovery (Martí and Pérez, 2015). However, this recuperation is still far to be acceptable with regard to the labor landscape (Casares and Vázquez, 2018). One of the main Spanish weaknesses that the crisis exposed was the so-called duality of the labor market. Thus, Spain is characterized by the existence of two very different types of workers. On one hand, long term workers on indefinite contracts, having both a very high job security and a very high cost for companies (especially in terms of dismissals) and usually with university studies even for jobs that do not require them.

We provide the first proof of convergence for normalized error feedback algorithms across a wide range of machine learning problems. Despite their popularity and efficiency in training deep neural networks, traditional analyses of error feedback algorithms rely on the smoothness assumption that does not capture the properties of objective functions in these problems. Rather, these problems have recently been shown to satisfy generalized smoothness assumptions, and the theoretical understanding of error feedback algorithms under these assumptions remains largely unexplored. Moreover, to the best of our knowledge, all existing analyses under generalized smoothness either i) focus on single-node settings or ii) make unrealistically strong assumptions for distributed settings, such as requiring data heterogeneity, and almost surely bounded stochastic gradient noise variance. In this paper, we propose distributed error feedback algorithms that utilize normalization to achieve the $O(1/\sqrt{K})$ convergence rate for nonconvex problems under generalized smoothness. Our analyses apply for distributed settings without data heterogeneity conditions, and enable stepsize tuning that is independent of problem parameters. Additionally, we provide strong convergence guarantees of normalized error feedback algorithms for stochastic settings. Finally, we show that due to their larger allowable stepsizes, our new normalized error feedback algorithms outperform their non-normalized counterparts on various tasks, including the minimization of polynomial functions, logistic regression, and ResNet-20 training.