Federal data shows identity theft losses can extend far beyond direct financial damage as victims spend weeks repairing credit files.

Federated learning poses new statistical and systems challenges in training machine learning models over distributed networks of devices. In this work, we show that multi-task learning is naturally suited to handle the statistical challenges of this setting, and propose a novel systems-aware optimization method, MOCHA, that is robust to practical systems issues. Our method and theory for the first time consider issues of high communication cost, stragglers, and fault tolerance for distributed multi-task learning. The resulting method achieves significant speedups compared to alternatives in the federated setting, as we demonstrate through simulations on real-world federated datasets.

We study the online learning problem of a bidder who participates in repeated auctions. With the goal of maximizing his T-period payoff, the bidder determines the optimal allocation of his budget among his bids for $K$ goods at each period. As a bidding strategy, we propose a polynomial-time algorithm, inspired by the dynamic programming approach to the knapsack problem. The proposed algorithm, referred to as dynamic programming on discrete set (DPDS), achieves a regret order of $O(\sqrt{T\log{T}})$. By showing that the regret is lower bounded by $\Omega(\sqrt{T})$ for any strategy, we conclude that DPDS is order optimal up to a $\sqrt{\log{T}}$ term. We evaluate the performance of DPDS empirically in the context of virtual trading in wholesale electricity markets by using historical data from the New York market. Empirical results show that DPDS consistently outperforms benchmark heuristic methods that are derived from machine learning and online learning approaches.

Navy robots from Gecko Robotics will inspect U.S. warships in $71 million effort to reduce maintenance delays as only 60% of fleet remains operational amid China's naval expansion.

Although text-to-image generation is rapidly advancing, these AI models are mostly English-centric. Researchers at the University of Amsterdam Faculty of Science have created NeoBabel, an AI image generator that can work in six different languages. By making all elements of their research open source, anyone can build on the model and help push inclusive AI research. When you generate an image with AI, the results are often better when your prompt is in English. This is because many AI models are English at their core: if you use another language, your prompt is translated into English before the image is created.

They said the company'has shown it is willing to... steal the intellectual property ofAmerican creators.' After ByteDance suspended the global rollout of its new Seedance 2.0 AI video generator on the weekend, US senators have now told the company to immediately shut down the app. Seedance 2.0 poses a direct threat to the American intellectual property system and, more broadly, to the constitutional rights and economic livelihoods of our creative community, Senators Marsha Blackburn and Peter Welch wrote in a letter to the company . Responsible global companies follow the law and respect core economic rights, including intellectual property and personal likeness protections, the senators wrote. They cited Seedance AI examples including an AI generated Thanos and Superman battle, a rewritten ending and that famous (fake) Tom Cruise and Brad Pitt battle .

Nonlinear independent component analysis (ICA) provides an appealing framework for unsupervised feature learning, but the models proposed so far are not identifiable. Here, we first propose a new intuitive principle of unsupervised deep learning from time series which uses the nonstationary structure of the data. Our learning principle, time-contrastive learning (TCL), finds a representation which allows optimal discrimination of time segments (windows). Surprisingly, we show how TCL can be related to a nonlinear ICA model, when ICA is redefined to include temporal nonstationarities. In particular, we show that TCL combined with linear ICA estimates the nonlinear ICA model up to point-wise transformations of the sources, and this solution is unique --- thus providing the first identifiability result for nonlinear ICA which is rigorous, constructive, as well as very general.

Joe Hogan, Align Technology's plastics-nerd CEO, says you shouldn't eat with your aligners and that you don't need to wear your retainers every night. Joe Hogan sees a lot of smiles. When people ask him where he works, he responds with "Align Technology," which inevitably prompts the follow up, "What's that?" After months, sometimes years, the discrete rival to braces promises to give people smiles they will want to show off. Hogan gets a look at them all. And he's eager to see more. Align is embarking on its biggest manufacturing overhaul since it was founded by two Stanford Graduate School of Business classmates 29 years ago. The company is preparing to begin directly 3D printing the aligners at the core of its business, ditching what Hogan describes as a longer, more wasteful process that involves making molds. A successful transition could lower costs and make treatment more affordable in the long run, bringing Invisalign to more customers and boosting Align's profits. It also, according to Hogan, would entrench Align as the world's biggest user of 3D printers .

We investigate the statistical performance and computational efficiency of the alternating minimization procedure for nonparametric tensor learning. Tensor modeling has been widely used for capturing the higher order relations between multimodal data sources. In addition to a linear model, a nonlinear tensor model has been received much attention recently because of its high flexibility. We consider an alternating minimization procedure for a general nonlinear model where the true function consists of components in a reproducing kernel Hilbert space (RKHS). In this paper, we show that the alternating minimization method achieves linear convergence as an optimization algorithm and that the generalization error of the resultant estimator yields the minimax optimality. We apply our algorithm to some multitask learning problems and show that the method actually shows favorable performances.

The recent success of deep neural networks relies on massive amounts of labeled data. For a target task where labeled data is unavailable, domain adaptation can transfer a learner from a different source domain. In this paper, we propose a new approach to domain adaptation in deep networks that can jointly learn adaptive classifiers and transferable features from labeled data in the source domain and unlabeled data in the target domain. We relax a shared-classifier assumption made by previous methods and assume that the source classifier and target classifier differ by a residual function. We enable classifier adaptation by plugging several layers into deep network to explicitly learn the residual function with reference to the target classifier. We fuse features of multiple layers with tensor product and embed them into reproducing kernel Hilbert spaces to match distributions for feature adaptation. The adaptation can be achieved in most feed-forward models by extending them with new residual layers and loss functions, which can be trained efficiently via back-propagation. Empirical evidence shows that the new approach outperforms state of the art methods on standard domain adaptation benchmarks.