In this paper, we study differentially private mechanisms for functions whose outputs lie in a Euclidean Jordan algebra. Euclidean Jordan algebras capture many important mathematical structures and form the foundation of linear programming, second-order cone programming, and semidefinite programming. Our main contribution is a generic Gaussian mechanism for such functions, with sensitivity measured in $\ell_2$, $\ell_1$, and $\ell_\infty$ norms. Notably, this framework includes the important case where the function outputs are symmetric matrices, and sensitivity is measured in the Frobenius, nuclear, or spectral norm. We further derive private algorithms for solving symmetric cone programs under various settings, using a combination of the multiplicative weights update method and our generic Gaussian mechanism. As an application, we present differentially private algorithms for semidefinite programming, resolving a major open question posed by [Hsu, Roth, Roughgarden, and Ullman, ICALP 2014].

Follow this author to personalize your feed and get instant alerts. Follow Go to your personalized feed WHY FOLLOW? Smart Alerts: Get notified about major news as it happens. Has anyone, in or out of the dentist's chair, shined more brightly after losing teeth than Jack Hughes, the New Jersey Devils center, who at the Milano Cortina Olympics scored the game-winning goal in overtime to give Team USA a 2-1 win over Canada, and the Americans their first men's hockey gold medal since the 1980 Miracle on Ice? Despite a high-stick to the mouth from Canada's Sam Bennett late in the third period, Hughes played on and fired a left-wing rocket past goalkeeper Jordan Binnington to seal the victory.

Finding approximations to an intractable probability distribution π of interest (usually known only up to a normalizing constant) is a key problem in scientific computing. Variational Inference stands out as a particularly attractive tool for this task, owing to its statistical and computational efficiency, and it has been the framework underlying many advances in computational statistics over the past half century (Parisi, 1980; Hinton and Van Camp, 1993; Jordan et al., 1999; Bishop and Nasrabadi, 2006). The central idea is to seek a tractable approximation to π within a chosen family of tractable distributions Q by minimizing a divergence to π over that'variational' family. Often, it is convenient or well-motivated to work with the family of product (or tensor, or factorized) distributions Q = P m, and define optimality through minimisation of the Kullback-Leibler (KL) divergence (also'relative entropy') min KL(ϱ||π): ϱ P m . A key practical aspect of working with this particular loss function is that in solving the associated optimisation problem, one is only required to compute expectations under the tractable variational distribution ϱ, rather than under the intractable target distribution π. In Bayesian statistics, π typically represents the joint posterior distribution of latent variables z Z and some parameters β B given observed data y Y. In these cases, we often choose m = 2 and seek the best variational approximation µ(dz) ν(dβ) to π to solve min KL(µ ν||π): µ P(Z), ν P(B) . The coordinate ascent variational inference algorithm (CAVI, Bishop and Nasrabadi, 2006; Blei et al., 2017) solves this problem by iteratively minimizing the Kullback-Leibler divergence with respect to one element at a time: given a starting point ν0, it iterates µk:= argmin

A year to go until France chooses its next president, the big question is who can save the election from being a battle of the extremes. For now, and perhaps only for now, the answer is pretty clear. It is President Emmanuel Macron's former prime minister, Edouard Philippe. Latest opinion polls concur that the 55-year-old centre-right politician is the only figure capable of beating a hard-right candidate in round two of the vote next May, whether that is Marine Le Pen or her young deputy Jordan Bardella. In any other polled scenario, the other candidate would lose and France would have a populist-right head of state.

In this section, we shall show detailed derivations for the point-wise dependency estimation methods. Four approaches are discussed: Variational Bounds of Mutual Information, Density Matching, Probabilistic Classifier, and Density-Ratio Fitting. For convenience, we define Ω = X Y. We have PX,Y and PXPY (can also be written as PX PY) be the probability measures over σ algebras over Ω with their probability densities being the Radon-Nikodym derivatives (i.e., p(x,y) = dPX,Y/dµ and p(x)p(y) = dPXPY/dµwith µbeing the Lebesgue measure). These estimators have the logarithm of point-wise dependency (PMI) as the intermediate product, which we will show in the following. We denote Mbe any class of functions m: Ω R. Proposition 1 (INWJ and its neural estimation, restating Nguyen-Wainwright-Jordan bound [5, 18]).

Fury as NYC on course to join Detroit, Chicago and Puerto Rico with woke mayor Mamdani's latest reckless plan Hidden $65bn lithium motherlode mapped beneath America's oldest mountains could power nation for centuries A quarter of US stock market gets report cards from Wall Street on same day this week. Even one bad grade can spell catastrophe for your 401(k). Here's EXACTLY what you need to do I was constantly burned out and kept cancelling plans because I was so tired. Doctors said it was just hormones... then I was diagnosed with this aggressive cancer. Nicole Kidman's daughters have'CUT OFF' dad Keith Urban: Insiders reveal why they are'SO angry'... and how he is utterly'distraught' but finally admitting'guilt' Florida go-kart park ordered to pay hefty settlement after mom and daughter, 6, broke two important rules that resulted in little girl's death King Charles leaves White House roaring with laughter with jokes to Trump about'speaking French' and the Boston Tea Party in dazzling state dinner Brace for the'Big Crunch': Scientists predict when the universe will end - and it's TRILLIONS of years sooner than we thought The $1.50 fruit that can protect you from deadly heart disease Why Donald Trump Jr and Bettina Anderson's wedding is'on hold' just weeks after extravagant'enchanted garden' bridal shower Serena Williams leaves fans split with controversial parenting confession as tennis legend opens up on'discipline' incident with daughter'No more Mr Nice Guy!': Trump warns Iran to'get smart' and'sign non-nuclear deal' with image of him brandishing assault rifle - as oil prices spike once more The surprise state cashing in big as Californians flee in droves... and the $672-a-month reason why What REALLY goes on in some Equinox steam rooms: Gym insiders reveal eye-popping indecency... secret towel signals used by experimental married men... and clubs with most'aggressive' locker rooms Fox News's Jesse Watters, 47, takes his young wife, 33, to state dinner after causing stir with story of how he seduced her Truth about Jordan Peterson's catastrophic decline: Inside his living hell, dumbstruck and in'overwhelming pain' locked up on $50m estate... as friends point finger about REAL cause Worrying shift as restaurant chain rolls out no-seating stores - sparking fears this is just the start of a'corporate purge of the American dining room' Shocking footage has revealed the moment a dancing robot went rogue at a school sports day.

There has been remarkable progress over the past decade in establishing finite-sample, non-asymptotic bounds on recovering unknown system parameters from observed system behavior. Surprisingly, however, we show that the current state-of-the-art bounds do not accurately capture the statistical complexity of system identification, even in the most fundamental setting of estimating a discrete-time linear dynamical system (LDS) via ordinary least-squares regression (OLS). Specifically, we utilize asymptotic normality to identify classes of problem instances for which current bounds overstate the squared parameter error, in both spectral and Frobenius norm, by a factor of the state-dimension of the system. Informed by this discrepancy, we then sharpen the OLS parameter error bounds via a novel second-order decomposition of the parameter error, where crucially the lower-order term is a matrix-valued martingale that we show correctly captures the CLT scaling. From our analysis we obtain finite-sample bounds for both (i) stable systems and (ii) the many-trajectories setting that match the instance-specific optimal rates up to constant factors in Frobenius norm, and polylogarithmic state-dimension factors in spectral norm.

We study the minimax sample complexity of multicalibration in the batch setting. A learner observes $n$ i.i.d. samples from an unknown distribution and must output a (possibly randomized) predictor whose population multicalibration error, measured by Expected Calibration Error (ECE), is at most $\varepsilon$ with respect to a given family of groups. For every fixed $κ> 0$, in the regime $|G|\le \varepsilon^{-κ}$, we prove that $\widetildeΘ(\varepsilon^{-3})$ samples are necessary and sufficient, up to polylogarithmic factors. The lower bound holds even for randomized predictors, and the upper bound is realized by a randomized predictor obtained via an online-to-batch reduction. This separates the sample complexity of multicalibration from that of marginal calibration, which scales as $\widetildeΘ(\varepsilon^{-2})$, and shows that mean-ECE multicalibration is as difficult in the batch setting as it is in the online setting, in contrast to marginal calibration which is strictly more difficult in the online setting. In contrast we observe that for $κ= 0$, the sample complexity of multicalibration remains $\widetildeΘ(\varepsilon^{-2})$ exhibiting a sharp threshold phenomenon. More generally, we establish matching upper and lower bounds, up to polylogarithmic factors, for a weighted $L_p$ multicalibration metric for all $1 \le p \le 2$, with optimal exponent $3/p$. We also extend the lower-bound template to a regular class of elicitable properties, and combine it with the online upper bounds of Hu et al. (2025) to obtain matching bounds for calibrating properties including expectiles and bounded-density quantiles.

When approximating an intractable density via variational inference (VI) the variational family is typically chosen as a simple parametric family that very likely does not contain the target. This raises the question: Under which conditions can we recover characteristics of the target despite misspecification? In this work, we extend previous results on robust VI with location-scale families under target symmetries. We derive sufficient conditions guaranteeing exact recovery of the mean when using the forward Kullback-Leibler divergence and $α$-divergences. We further show how and why optimization can fail to recover the target mean in the absence of our sufficient conditions, providing initial guidelines on the choice of the variational family and $α$-value.

We study semisupervised mean estimation with a small labeled sample, a large unlabeled sample, and a black-box prediction model whose output may be miscalibrated. A standard approach in this setting is augmented inverse-probability weighting (AIPW) [Robins et al., 1994], which protects against prediction-model misspecification but can be inefficient when the prediction score is poorly aligned with the outcome scale. We introduce Calibrated Prediction-Powered Inference, which post-hoc calibrates the prediction score on the labeled sample before using it for semisupervised estimation. This simple step requires no retraining and can improve the original score both as a predictor of the outcome and as a regression adjustment for semisupervised inference. We study both linear and isotonic calibration. For isotonic calibration, we establish first-order optimality guarantees: isotonic post-processing can improve predictive accuracy and estimator efficiency relative to the original score and simpler post-processing rules, while no further post-processing of the fitted isotonic score yields additional first-order gains. For linear calibration, we show first-order equivalence to PPI++. We also clarify the relationship among existing estimators, showing that the original PPI estimator is a special case of AIPW and can be inefficient when the prediction model is accurate, while PPI++ is AIPW with empirical efficiency maximization [Rubin et al., 2008]. In simulations and real-data experiments, our calibrated estimators often outperform PPI and are competitive with, or outperform, AIPW and PPI++. We provide an accompanying Python package, ppi_aipw, at https://larsvanderlaan.github.io/ppi-aipw/.