We consider the problem of Learning from Label Proportions (LLP), a weakly supervised classification setup where instances are grouped into i.i.d. "bags", and only the frequency of class labels at each bag is available. Albeit, the objective of the learner is to achieve low task loss at an individual instance level. Here we propose EASYLLP, a flexible and simple-to-implement debiasing approach based on aggregate labels, which operates on arbitrary loss functions. Our technique allows us to accurately estimate the expected loss of an arbitrary model at an individual level. We elucidate the differences between our method and standard methods based on label proportion matching, in terms of applicability and optimality conditions. We showcase the flexibility of our approach compared to alternatives by applying our method to popular learning frameworks, like Empirical Risk Minimization (ERM) and Stochastic Gradient Descent (SGD) with provable guarantees on instance level performance.

When you purchase through links in our articles, we may earn a small commission. Thinking of switching from MacBook? RTX 5070 laptops deliver faster creative performance, powerful AI features and next-level gaming - built for demanding workflows. Apple's MacBooks are icons of the creative arts, and are beloved by creatives for their performance and streamlined design. But as capable as they are, they don't offer the same kind of power and versatility as the latest RTX AI PCs equipped with NVIDIA's GeForce RTX 50 Series graphics cards. If you're considering a laptop upgrade this year, GeForce RTX 50 Series laptops, backed by the latest Blackwell architecture, are specifically designed to handle the most demanding creative projects, outperforming the competition in both speed and visual precision.

"A.I. is happening rapidly, and we didn't help people cope with globalization and technological change very well over a 30- and 40-year period," Mr. Hubbard explained. "We're probably not going to do it again." Policymakers across Washington generally agree that A.I. portends generational change, with vast implications for everything from medical research to warfare. That has helped spark an investment boom in computing, and a burst of new growth for the broader economy, which Mr. Trump has tried to maximize. Through a series of executive orders, signed over the last 11 months, Mr. Trump has moved to eliminate regulatory guardrails and make it easier for tech companies to build data centers, power their operations, sell computer chips and source critical materials.

A surge of AI-generated content is frustrating Pinterest users and left some questioning whether the platform still works at all. For five years, Caitlyn Jones has used Pinterest on a weekly basis to find recipes for her son. In September, Jones spotted a creamy chicken and broccoli slow-cooker recipe, sprinkled with golden cheddar and a pop of parsley. She quickly looked at the ingredients and added them to her grocery list. But just as she was about to start cooking, having already bought everything, one thing stood out: The recipe told her to start by "logging" the chicken into the slow cooker.

Entropic causal inference is a framework for inferring the causal direction between two categorical variables from observational data. The central assumption is that the amount of unobserved randomness in the system is not too large. This unobserved randomness is measured by the entropy of the exogenous variable in the underlying structural causal model, which governs the causal relation between the observed variables. Kocaoglu et al. conjectured that the causal direction is identifiable when the entropy of the exogenous variable is not too large. In this paper, we prove a variant of their conjecture.

The mysteries of Christmas might that parcel be game or console-shaped? The mysteries of Christmas might that parcel be game or console-shaped? 'I plugged in Zelda and everything changed': developers share their fondest Christmas gaming memories From a family showdown on Guitar Hero III to the winter levels in Diddy Kong Racing, the designers of some of today's top titles recall the gifts and moments that lit up their childhoods T here is a viral video that tends to get passed around at this time of year. It's an old home movie showing a boy and a girl on Christmas morning eagerly unwrapping a present that turns out to be an N64 console - the boy is, to put it mildly, extremely pleased. It's a scene a lot of us who play games will recognise: the excitement and anticipation provided by that big console-sized parcel, or the little DVD-shaped package that could be the latest Super Mario adventure.

WIRED spoke with DeepMind's Pushmeet Kohli about the recent past--and promising future--of the Nobel Prize-winning research project that changed biology and chemistry forever. Amino acids "folded" to form a protein. Over the past few years, we've periodically reported on its successes; last year, it won the Nobel Prize in Chemistry . Until AlphaFold's debut in November 2020, DeepMind had been best known for teaching an artificial intelligence to beat human champions at the ancient game of Go Its work culminated in the compilation of a database that now contains over 200 million predicted structures, essentially the entire known protein universe, and is used by nearly 3.5 million researchers in 190 countries around the world The Nature article published in 2021 describing the algorithm has been cited 40,000 times to date. Last year, AlphaFold 3 arrived, extending the capabilities of artificial intelligence to DNA, RNA, and drugs.

Actor-critic (AC) algorithms, empowered by neural networks, have had significant empirical success in recent years. However, most of the existing theoretical support for AC algorithms focuses on the case of linear function approximations, or linearized neural networks, where the feature representation is fixed throughout training. Such a limitation fails to capture the key aspect of representation learning in neural AC, which is pivotal in practical problems. In this work, we take a mean-field perspective on the evolution and convergence of feature-based neural AC. Specifically, we consider a version of AC where the actor and critic are represented by overparameterized two-layer neural networks and are updated with two-timescale learning rates. The critic is updated by temporal-difference (TD) learning with a larger stepsize while the actor is updated via proximal policy optimization (PPO) with a smaller stepsize. In the continuous-time and infinite-width limiting regime, when the timescales are properly separated, we prove that neural AC finds the globally optimal policy at a sublinear rate. Additionally, we prove that the feature representation induced by the critic network is allowed to evolve within a neighborhood of the initial one.

Language is an important tool for humans to share knowledge. We propose a meta-learning method that shares knowledge across supervised learning tasks using feature descriptions written in natural language, which have not been used in the existing meta-learning methods. The proposed method improves the predictive performance on unseen tasks with a limited number of labeled data by meta-learning from various tasks. With the feature descriptions, we can find relationships across tasks even when their feature spaces are different. The feature descriptions are encoded using a language model pretrained with a large corpus, which enables us to incorporate human knowledge stored in the corpus into meta-learning. In our experiments, we demonstrate that the proposed method achieves better predictive performance than the existing meta-learning methods using a wide variety of real-world datasets provided by the statistical office of the EU and Japan.

Accurate estimation of predictive uncertainty (model calibration) is essential for the safe application of neural networks. Many instances of miscalibration in modern neural networks have been reported, suggesting a trend that newer, more accurate models produce poorly calibrated predictions. Here, we revisit this question for recent state-of-the-art image classification models. We systematically relate model calibration and accuracy, and find that the most recent models, notably those not using convolutions, are among the best calibrated. Trends observed in prior model generations, such as decay of calibration with distribution shift or model size, are less pronounced in recent architectures. We also show that model size and amount of pretraining do not fully explain these differences, suggesting that architecture is a major determinant of calibration properties.