Survival analysis on tabular data is a well-studied problem. However, existing deep learning methods are often highly task-specific, which can limit the transfer of new approaches from other domains and introduce constraints that may affect performance. We propose TabSurv, an approach that adapts modern tabular architectures to survival analysis using either the Weibull distribution or non-parametric survival prediction. TabSurv optimizes SurvHL, a novel histogram loss function supporting censored data. In addition to a baseline feed-forward network, we implement deep ensembles of MLPs for survival analysis within TabSurv. In contrast to prior work, the ensemble components are trained in parallel, optimizing survival distribution parameters before averaging, which promotes diversity across ensemble component predictions. We perform a comprehensive empirical evaluation of different proposed architectures on 10 diverse real-world survival datasets. Our results show that TabSurv consistently outperforms on average established classical and deep learning baselines, such as RSF, DeepSurv, DeepHit, SurvTRACE. Notably, deep ensembles with Weibull parametrization instead of non-parametric models achieve the highest average rank by C-index. Overall, our study clarifies how modern tabular neural networks can be adapted and trained to tackle survival analysis problems, offering a strong and reliable approach. The TabSurv implementation is publicly available.

Standard differential privacy imposes uniform privacy constraints across all features, overlooking the inherent distinction between sensitive and insensitive features in practice. In this paper, we introduce a relaxed definition of differential privacy that accounts for such heterogeneity, allowing certain features to be treated as insensitive even when correlated with sensitive ones. We propose a correlation-aware framework, $\textsf{CorrDP}$, which relaxes privacy for insensitive features while accounting for their correlations with sensitive features, with the correlations quantified using total variation distance. We design algorithms for differentially private empirical risk minimization (DP-ERM) under the $\textsf{CorrDP}$ framework, incorporating distance-dependent noise into gradients for improved theoretical utility guarantees. When the correlation distance is unknown, we estimate it from the dataset and show that it achieves a comparable privacy-utility guarantee. We perform experiments on synthetic and real-world datasets and show that $\textsf{CorrDP}$-based DP-ERM algorithms consistently outperform the standard DP framework in the presence of insensitive features.

Sampling from unnormalized multimodal distributions with limited density evaluations remains a fundamental challenge in machine learning and natural sciences. Successful approaches construct a bridge between a tractable reference and the target distribution. Parallel Tempering (PT) serves as the gold standard, while recent diffusion-based approaches offer a continuous alternative at the cost of neural training. In this work, we introduce Conditional Diffusion Sampling (CDS), a framework that combines these two paradigms. To this end, we derive Conditional Interpolants, a class of stochastic processes whose transport dynamics are governed by an exact, closed-form stochastic differential equation (SDE), requiring no neural approximation. Although these dynamics require sampling from a non-trivial initialization distribution, we show both theoretically and empirically that the cost of this initialization diminishes for sufficiently short diffusion times. CDS leverages this by a two-stage procedure: (1) PT is used to efficiently sample the initial distribution, and then (2) samples are transported via the transport SDE. This combination couples the robust global exploration of PT with efficient local transport. Experiments suggest that CDS has the potential to achieve a superior trade-off between sample quality and density evaluation cost compared to state-of-the-art samplers.

Things to Do in L.A. Tap to enable a layout that focuses on the article. The gift will rename USC's School of Advanced Computing as the USC Mark and Mary Stevens School of Computing and Artificial Intelligence. This is read by an automated voice. Please report any issues or inconsistencies here . USC receives a $200-million gift from venture capitalist Mark Stevens to establish artificial intelligence research and expertise across campus.

A top Google scientist warned EU antitrust regulators that its proposal requiring the company to share search engine data with rivals risked exposing users' private information. BRUSSELS - A top Google scientist sent a warning to EU antitrust regulators on Tuesday that its proposal requiring the company to share search engine data with rivals such as OpenAI risked exposing users' private information, the sternest rebuke yet in a tussle over Google's lucrative business model. The European Commission, which acts as the EU competition enforcer, has in recent years cracked down on Big Tech via a slew of legislation to ensure that users have more choices and that smaller rivals have room to compete. However, that has triggered the ire of the U.S. government. Sergei Vassilvitskii, with the title of distinguished scientist at Google since 2012 and regarded a leader in his field, will meet EU antitrust officials on Wednesday to voice his concerns and propose a broader approach with better guardrails.

We learned earlier this month that Google and Anthropic had inked a deal that would grant the creator of the Claude AI models access to cloud servers and chips. Today, reported that Anthropic has agreed to pay a staggering $200 billion to Google over the next five years. Contracts like this, or Anthropic's other recent multi-billion dollar arrangement with Amazon, now account for a ludicrous amount of money promised to some of the world's largest tech companies. These cloud service providers have been early investors in the AI boom, gambling that the startups' need for their resources as they grow would yield lucrative dividends. So far, they've been correct.

Fashion I Used to Love the Met Gala. Then the World's Most Evil Couple Ruined It for Everyone. I don't really care to see an OpenAI employee walk the red carpet. Enter your email to receive alerts for this author. You can manage your newsletter subscriptions at any time.

Xbox is ditching Microsoft's Copilot AI Xbox is ditching Microsoft's Copilot AI Microsoft announced plans to start stripping Copilot out of select Windows apps in March after criticism of the company's mishandling of its operating system reached a fever pitch. As it turns out though, Windows isn't the only place where you'll see less Copilot: Xbox CEO Asha Sharma has announced that the AI assistant will also be removed from the gaming brand's mobile app and Xbox consoles. Under previous Xbox leadership, Copilot was introduced as a sort of in-game assistant that would be aware of what you're playing and able to offer contextual advice based on what's on your screen. Microsoft launched a beta version of the experience by adding Copilot to the Xbox mobile app in May 2025, but based on a GDC presentation the company gave in March, the plan was to also bring Copilot to Xbox consoles later this year. Those plans apparently don't align with where Xbox is headed, Sharma said in a post announcing new hires to the Xbox division.

Courts may restrict access to the popular abortion medication mifepristone in the United States. Telehealth providers have backup plans in place. Abortion provider Carafem's phones were ringing nonstop over the weekend after a US federal appeals court reinstated a nationwide requirement that the drug mifepristone, one of two pills used for a medication abortion, must be obtained in person. The decision, handed down on Friday, left patients unsure if they could gain access to their treatment through telehealth. "People are afraid, and they're angry," says Carafem's chief operations officer, Melissa Grant. "I had people contact us saying, .

It may not be a fully-fledged protocol droid yet, but Luke Skywalker would be impressed. More information Adding us as a Preferred Source in Google by using this link indicates that you would like to see more of our content in Google News results. Breakthroughs, discoveries, and DIY tips sent six days a week. Convincing, uncannily humanoid robots are no longer the stuff of . Sure, you may not have a protocol droid at your ready like the iconic (if neurotic) C-3PO,but you can certainly construct a computer model that imitates Luke Skywalker's mechanical pal.