Regularization is one of the most fundamental topics in optimization, statistics and machine learning.

The Model S deserved better than this. Before Elon Musk, most electric vehicles seemed less like an alternative to gasoline than an argument in its favor. The sad state of affairs for EVs for many years was that they were slow, impractical, and largely enticing only if you lived with copious guilt over your carbon emissions. Then Tesla came out with the Tesla Model S. The speedy, high-tech sedan didn't just leave other EVs in the dust; it could compete with the likes of BMW and Mercedes-Benz. "EVs went from'eating your vegetables' to getting you super-car performance in a vehicle that's luxurious and quiet," Jake Fisher, the senior director of auto testing at Consumer Reports, told me.

Stock market prediction is a long-standing challenge in finance, as accurate forecasts support informed investment decisions. Traditional models rely mainly on historical prices, but recent work shows that financial news can provide useful external signals. This paper investigates a multimodal approach that integrates companies' news articles with their historical stock data to improve prediction performance. We compare a Graph Neural Network (GNN) model with a baseline LSTM model. Historical data for each company is encoded using an LSTM, while news titles are embedded with a language model. These embeddings form nodes in a heterogeneous graph, and GraphSAGE is used to capture interactions between articles, companies, and industries. We evaluate two targets: a binary direction-of-change label and a significance-based label. Experiments on the US equities and Bloomberg datasets show that the GNN outperforms the LSTM baseline, achieving 53% accuracy on the first target and a 4% precision gain on the second. Results also indicate that companies with more associated news yield higher prediction accuracy. Moreover, headlines contain stronger predictive signals than full articles, suggesting that concise news summaries play an important role in short-term market reactions.

The aim of this paper is the analysis and selection of stock trading systems that combine different models with data of different nature, such as financial and microeconomic information. Specifically, based on previous work by the authors and applying advanced techniques of Machine Learning and Deep Learning, our objective is to formulate trading algorithms for the stock market with empirically tested statistical advantages, thus improving results published in the literature. Our approach integrates Long Short-Term Memory (LSTM) networks with algorithms based on decision trees, such as Random Forest and Gradient Boosting. While the former analyze price patterns of financial assets, the latter are fed with economic data of companies. Numerical simulations of algorithmic trading with data from international companies and 10-weekday predictions confirm that an approach based on both fundamental and technical variables can outperform the usual approaches, which do not combine those two types of variables. In doing so, Random Forest turned out to be the best performer among the decision trees. We also discuss how the prediction performance of such a hybrid approach can be boosted by selecting the technical variables.

Understanding sentiment in financial documents is crucial for gaining insights into market behavior. These reports often contain obfuscated language designed to present a positive or neutral outlook, even when underlying conditions may be less favorable. This paper presents a novel approach using Aspect-Based Sentiment Analysis (ABSA) to decode obfuscated sentiment in Thai financial annual reports. We develop specific guidelines for annotating obfuscated sentiment in these texts and annotate more than one hundred financial reports. We then benchmark various text classification models on this annotated dataset, demonstrating strong performance in sentiment classification. Additionally, we conduct an event study to evaluate the real-world implications of our sentiment analysis on stock prices. Our results suggest that market reactions are selectively influenced by specific aspects within the reports. Our findings underscore the complexity of sentiment analysis in financial texts and highlight the importance of addressing obfuscated language to accurately assess market sentiment.

Nvidia becomes world's first $5tn company amid stock market and AI boom Nvidia has become the world's first $5tn company, just three months after the Silicon Valley chipmaker was first to break through the barrier of $4tn in market value. In comparison, Nvidia's value is greater than the GDP of India, Japan and the United Kingdom, according to the International Monetary Fund (IMF). Shortly after US stock markets opened on Wednesday, Nvidia's shares touched $207.86 with 24.3bn shares outstanding, putting its market cap at $5.05tn. Ravenous appetite for Nvidia's chips, seen as the most cutting edge in powering artificial intelligence products and software, is the main reason that the company's stock price has increased so rapidly since early 2023. The wider US stock market has reached multiple record highs this week, buoyed up by expansive investment in artificial intelligence.

Aligning large language models with human feedback at inference time has received increasing attention due to its flexibility. Existing methods rely on generating multiple responses from the base policy for search using a reward model, which can be considered as searching in a discrete response space. However, these methods struggle to explore informative candidates when the base policy is weak or the candidate set is small, resulting in limited effectiveness. In this paper, to address this problem, we propose Simple Energy Adaptation ($\textbf{SEA}$), a simple yet effective algorithm for inference-time alignment. In contrast to expensive search over the discrete space, SEA directly adapts original responses from the base policy toward the optimal one via gradient-based sampling in continuous latent space. Specifically, SEA formulates inference as an iterative optimization procedure on an energy function over actions in the continuous space defined by the optimal policy, enabling simple and effective alignment. For instance, despite its simplicity, SEA outperforms the second-best baseline with a relative improvement of up to $ \textbf{77.51%}$ on AdvBench and $\textbf{16.36%}$ on MATH. Our code is publicly available at https://github.com/yuanyige/sea

Trump's Investment in Intel Is Paying Off The chipmaker reported higher than expected revenue on Thursday, and its stock price has risen over 90 percent since August. The Trump administration's investment in Intel appears to be paying off so far, but the once-mighty chipmaker still has a long way to climb back to industry dominance. In August, the US government announced it was converting about $9 billion in federal grants that Intel had been issued during the Biden administration into a roughly 10 percent equity stake in the company. During its third-quarter earnings on Thursday--its first financial update since Trump's surprise investment--Intel reported that it earned $13.7 billion in revenue over the past three months, a three percent increase year-over-year. It's the fourth consecutive quarter that Intel has beat revenue guidance.