arXiv subjects

Yuval Dagan

Publications and source records attributed to Yuval Dagan.

At least 19 recordsLinked to original sources

arXiv2026

Efficient dispersal of submicron solid particles for stratospheric aerosol injection

Stratospheric aerosol injection (SAI) using solid particles has been proposed as an alternative to sulfate aerosols for solar radiation modification, but practical deployment faces challenges in efficiently deagglomerating and dispersing powders as submicron particles. Here we experimentally demonstrate pneumatic dispersal of particles in optically optimal size ranges for SAI. Using spherical amorphous silica particles, we find that applying a hydrophobic surface treatment substantially improves dispersibility, with 50-85% of treated particle mass achieving submicron sizes compared to 10% for untreated particles. We compare the dispersal of treated particles of different sizes and find that 300 nm particles provide superior deagglomeration than 500 nm particles for the same air consumption. Theoretical modeling of the adhesion forces between particles, combined with surface roughness parameters extracted from atomic force microscopy, successfully predicted the relative dispersibility across different particle types. The pneumatic dispersal system achieved optimal performance at air-to-powder mass ratios of about 10:1. Using the measured dispersed particle sizes, we provide a scaling analysis suggesting that a feasibly sized fleet of dispersal aircraft could provide an aerosol layer sufficient for meaningful climate intervention. These results demonstrate that hydrophobic surface treatment and pneumatic dispersal can overcome the agglomeration challenge for SAI with solid particles.

physics.app-ph↗

arXiv2025

Learning Local Stackelberg Equilibria from Repeated Interactions with a Learning Agent

Motivated by the question of how a principal can maximize its utility in repeated interactions with a learning agent, we study repeated games between an principal and an agent employing a mean-based learning algorithm. Prior work has shown that computing or even approximating the global Stackelberg value in similar settings can require an exponential number of rounds in the size of the agent's action space, making it computationally intractable. In contrast, we shift focus to the computation of local Stackelberg equilibria and introduce an algorithm that, within the smoothed analysis framework, constitutes a Polynomial Time Approximation Scheme (PTAS) for finding an epsilon-approximate local Stackelberg equilibrium. Notably, the algorithm's runtime is polynomial in the size of the agent's action space yet exponential in (1/epsilon) - a dependency we prove to be unavoidable.

cs.GT↗

arXiv2025

Heavy Particle Motion in Rotational Vortices

This study examines the motion of spherical inertial particles in a three-dimensional rotating cylindrical vortex - a simplified model of geophysical flow structures such as oceanic eddies. The analytical vortex formulation enables the isolation of the key mechanisms that govern particle transport in rotating flows. Using Lagrangian particle tracking simulations, we investigate the influence of drag, buoyancy, virtual mass, Coriolis, and Magnus lift forces across a range of particle sizes, densities, and vortex rotation rates. Results show that particle aggregation and periodic stability depend on both particle inertia and flow parameters. Rotational lift forces, though often neglected for spherical particles, become dominant at moderate particle Stokes numbers and introduce slow vertical oscillations in both particle position and spin. The balance of forces determines whether particles settle into stable periodic orbits or escape the vortex. Our analysis reveals unique equilibrium positions that exhibit bifurcations, with multiple or vanishing steady states depending on particle and flow characteristics. Our results demonstrate how particle aggregation and orbital stability stem from the complex coupling between rotational lift, Coriolis, drag, buoyancy, and virtual mass forces. This model may promote informed modeling of dispersed phase transport in marine flows and industrial mixing processes.

physics.flu-dyn↗

arXiv2025

Computational Intractability of Strategizing against Online Learners

Online learning algorithms are widely used in strategic multi-agent settings, including repeated auctions, contract design, and pricing competitions, where agents adapt their strategies over time. A key question in such environments is how an optimizing agent can best respond to a learning agent to improve its own long-term outcomes. While prior work has developed efficient algorithms for the optimizer in special cases - such as structured auction settings or contract design - no general efficient algorithm is known. In this paper, we establish a strong computational hardness result: unless $\mathsf{P} = \mathsf{NP}$, no polynomial-time optimizer can compute a near-optimal strategy against a learner using a standard no-regret algorithm, specifically Multiplicative Weights Update (MWU). Our result proves an $\Omega(T)$ hardness bound, significantly strengthening previous work that only showed an additive $\Theta(1)$ impossibility result. Furthermore, while the prior hardness result focused on learners using fictitious play - an algorithm that is not no-regret - we prove intractability for a widely used no-regret learning algorithm. This establishes a fundamental computational barrier to finding optimal strategies in general game-theoretic settings.

cs.GT↗

arXiv2025

Fixed Point Computation: Beating Brute Force with Smoothed Analysis

We propose a new algorithm that finds an $\varepsilon$-approximate fixed point of a smooth function from the $n$-dimensional $\ell_2$ unit ball to itself. We use the general framework of finding approximate solutions to a variational inequality, a problem that subsumes fixed point computation and the computation of a Nash Equilibrium. The algorithm's runtime is bounded by $e^{O(n)}/\varepsilon$, under the smoothed-analysis framework. This is the first known algorithm in such a generality whose runtime is faster than $(1/\varepsilon)^{O(n)}$, which is a time that suffices for an exhaustive search. We complement this result with a lower bound of $e^{\Omega(n)}$ on the query complexity for finding an $O(1)$-approximate fixed point on the unit ball, which holds even in the smoothed-analysis model, yet without the assumption that the function is smooth. Existing lower bounds are only known for the hypercube, and adapting them to the ball does not give non-trivial results even for finding $O(1/\sqrt{n})$-approximate fixed points.

cs.GT↗

arXiv2024

Dimension-free Private Mean Estimation for Anisotropic Distributions

We present differentially private algorithms for high-dimensional mean estimation. Previous private estimators on distributions over $\mathbb{R}^d$ suffer from a curse of dimensionality, as they require $\Omega(d^{1/2})$ samples to achieve non-trivial error, even in cases where $O(1)$ samples suffice without privacy. This rate is unavoidable when the distribution is isotropic, namely, when the covariance is a multiple of the identity matrix, or when accuracy is measured with respect to the affine-invariant Mahalanobis distance. Yet, real-world data is often highly anisotropic, with signals concentrated on a small number of principal components. We develop estimators that are appropriate for such signals$\unicode{x2013}$our estimators are $(\varepsilon,\delta)$-differentially private and have sample complexity that is dimension-independent for anisotropic subgaussian distributions. Given $n$ samples from a distribution with known covariance-proxy $\Sigma$ and unknown mean $\mu$, we present an estimator $\hat{\mu}$ that achieves error $\|\hat{\mu}-\mu\|_2\leq \alpha$, as long as $n\gtrsim\mathrm{tr}(\Sigma)/\alpha^2+ \mathrm{tr}(\Sigma^{1/2})/(\alpha\varepsilon)$. In particular, when $\pmb{\sigma}^2=(\sigma_1^2, \ldots, \sigma_d^2)$ are the singular values of $\Sigma$, we have $\mathrm{tr}(\Sigma)=\|\pmb{\sigma}\|_2^2$ and $\mathrm{tr}(\Sigma^{1/2})=\|\pmb{\sigma}\|_1$, and hence our bound avoids dimension-dependence when the signal is concentrated in a few principal components. We show that this is the optimal sample complexity for this task up to logarithmic factors. Moreover, for the case of unknown covariance, we present an algorithm whose sample complexity has improved dependence on the dimension, from $d^{1/2}$ to $d^{1/4}$.

cs.LG↗

arXiv2024

Quantum Particle Statistics in Classical Shallow Water Waves

We present a new hydrodynamic analogy of nonrelativistic quantum particles in potential wells. Similarities between a real variant of the Schr\"odinger equation and gravity-capillary shallow water waves are reported and analyzed. We show that when locally oscillating particles are guided by real wave gradients, particles may exhibit trajectories of alternating periodic or chaotic dynamics while increasing the wave potential. The particle probability distribution function of this analogy reveals the quantum statistics of the standard solutions of the Schr\"odinger equation and thus manifests as a classical deterministic interpretation of Born's rule. Finally, a classical mechanism for the transition between quasi-stationary states is proposed.

quant-ph↗

arXiv2024

Direct numerical simulation of particle clustering and turbulence modulation: an Eulerian approach

We present a new Eulerian framework for the computation of turbulent compressible multiphase channel flows, specifically to assess turbulence modulation by dispersed particulate matter in dilute concentrations but with significant mass loadings. By combining a modified low-dissipation numerical scheme for the carrier gas phase and a quadrature-based moment method for the solid particle phase, turbulent statistics of the fluid phase and fluctuations of the particle phase may be obtained as both are resolved as coupled fields. Using direct numerical simulations, we demonstrate how this method effectively resolves the turbulent statistics, kinetic energy, skin friction drag, particle mass flow rate and interphase drag for moderate-Reynolds-number channel flows for the first time. Validation of our approach to the turbulent particle-free flow and the turbulent particle-laden flow proves the applicability of the carrier flow low-dissipation scheme to simulate relatively low-Mach-number compressible flows and of the quadrature-based moment method to simulate the particle phase as an Eulerian field. This study also rationalises the computed interphase drag modulation and total Reynolds shear stress results using a simplified analytical approach, revealing how the particle migration towards the wall can affect the drag between the two phases at different Stokes numbers and particle loadings. Furthermore, we show the effect of near-wall particle accumulation on the particle mass flow rate. Using our Eulerian approach, we also explore the complex interplay between the particles and turbulent fluctuations by capturing the preferential clustering of particles in turbulence streaks. This interplay leads to turbulence modulations similar to recent observations reported in prior computational works using Lagrangian simulations.

physics.flu-dyn↗

arXiv2024

Maximizing utility in multi-agent environments by anticipating the behavior of other learners

Learning algorithms are often used to make decisions in sequential decision-making environments. In multi-agent settings, the decisions of each agent can affect the utilities/losses of the other agents. Therefore, if an agent is good at anticipating the behavior of the other agents, in particular how they will make decisions in each round as a function of their experience that far, it could try to judiciously make its own decisions over the rounds of the interaction so as to influence the other agents to behave in a way that ultimately benefits its own utility. In this paper, we study repeated two-player games involving two types of agents: a learner, which employs an online learning algorithm to choose its strategy in each round; and an optimizer, which knows the learner's utility function and the learner's online learning algorithm. The optimizer wants to plan ahead to maximize its own utility, while taking into account the learner's behavior. We provide two results: a positive result for repeated zero-sum games and a negative result for repeated general-sum games. Our positive result is an algorithm for the optimizer, which exactly maximizes its utility against a learner that plays the Replicator Dynamics -- the continuous-time analogue of Multiplicative Weights Update (MWU). Additionally, we use this result to provide an algorithm for the optimizer against MWU, i.e.~for the discrete-time setting, which guarantees an average utility for the optimizer that is higher than the value of the one-shot game. Our negative result shows that, unless P=NP, there is no Fully Polynomial Time Approximation Scheme (FPTAS) for maximizing the utility of an optimizer against a learner that best-responds to the history in each round. Yet, this still leaves open the question of whether there exists a polynomial-time algorithm that optimizes the utility up to $o(T)$.

cs.GT↗

arXiv2024

Breaking the $T^{2/3}$ Barrier for Sequential Calibration

A set of probabilistic forecasts is calibrated if each prediction of the forecaster closely approximates the empirical distribution of outcomes on the subset of timesteps where that prediction was made. We study the fundamental problem of online calibrated forecasting of binary sequences, which was initially studied by Foster & Vohra (1998). They derived an algorithm with $O(T^{2/3})$ calibration error after $T$ time steps, and showed a lower bound of $\Omega(T^{1/2})$. These bounds remained stagnant for two decades, until Qiao & Valiant (2021) improved the lower bound to $\Omega(T^{0.528})$ by introducing a combinatorial game called sign preservation and showing that lower bounds for this game imply lower bounds for calibration. In this paper, we give the first improvement to the $O(T^{2/3})$ upper bound on calibration error of Foster & Vohra. We do this by introducing a variant of Qiao & Valiant's game that we call sign preservation with reuse (SPR). We prove that the relationship between SPR and calibrated forecasting is bidirectional: not only do lower bounds for SPR translate into lower bounds for calibration, but algorithms for SPR also translate into new algorithms for calibrated forecasting. We then give an improved \emph{upper bound} for the SPR game, which implies, via our equivalence, a forecasting algorithm with calibration error $O(T^{2/3 - \varepsilon})$ for some $\varepsilon > 0$, improving Foster & Vohra's upper bound for the first time. Using similar ideas, we then prove a slightly stronger lower bound than that of Qiao & Valiant, namely $\Omega(T^{0.54389})$. Our lower bound is obtained by an oblivious adversary, marking the first $\omega(T^{1/2})$ calibration lower bound for oblivious adversaries.

cs.LG↗

arXiv2024

On the early stages of vapor bubble growth: From the surface-tension to the inertial regime

This paper presents a new analytical model for the early stages of vapor bubble growth in superheated liquids. The model bridges a gap in current knowledge by focusing on the surface tension-controlled, near-equilibrium growth regime and its transition to an inertia-controlled regime. A unified analytical model is derived by combining a perturbation method for the initial growth regime with a complementary outer solution to model the subsequent bubble growth rate. The model successfully predicts the initial delay in bubble growth due to surface tension effects. Two non-dimensional parameters govern this delay period: the initial perturbation from the equilibrium radius and the Ohnesorge number at the onset of nucleation. The Ohnesorge number encapsulates the interplay between viscous damping and surface tension forces acting on the bubble during its early growth stages. The analytical solutions presented here allow for quantifying the surface-tension, inertial, and transitional regimes while establishing a simple criterion for estimating the influence of thermal effects on early-stage growth. Our findings emphasize the significance of considering the surface tension delay, particularly for short timescales. The derived analytical solutions and the obtained correlation for surface-tension-induced delay may prove a practical tool and could be integrated into existing models of vapor bubble growth.

physics.flu-dyn↗

arXiv2023

From External to Swap Regret 2.0: An Efficient Reduction and Oblivious Adversary for Large Action Spaces

We provide a novel reduction from swap-regret minimization to external-regret minimization, which improves upon the classical reductions of Blum-Mansour [BM07] and Stolz-Lugosi [SL05] in that it does not require finiteness of the space of actions. We show that, whenever there exists a no-external-regret algorithm for some hypothesis class, there must also exist a no-swap-regret algorithm for that same class. For the problem of learning with expert advice, our result implies that it is possible to guarantee that the swap regret is bounded by {\epsilon} after $\log(N)^{O(1/\epsilon)}$ rounds and with $O(N)$ per iteration complexity, where $N$ is the number of experts, while the classical reductions of Blum-Mansour and Stolz-Lugosi require $O(N/\epsilon^2)$ rounds and at least $\Omega(N^2)$ per iteration complexity. Our result comes with an associated lower bound, which -- in contrast to that in [BM07] -- holds for oblivious and $\ell_1$-constrained adversaries and learners that can employ distributions over experts, showing that the number of rounds must be $\tilde\Omega(N/\epsilon^2)$ or exponential in $1/\epsilon$. Our reduction implies that, if no-regret learning is possible in some game, then this game must have approximate correlated equilibria, of arbitrarily good approximation. This strengthens the folklore implication of no-regret learning that approximate coarse correlated equilibria exist. Importantly, it provides a sufficient condition for the existence of correlated equilibrium which vastly extends the requirement that the action set is finite, thus answering a question left open by [DG22; Ass+23]. Moreover, it answers several outstanding questions about equilibrium computation and learning in games.

cs.LG↗

arXiv2023

Hydrodynamically Inspired Pilot-Wave Theory: An Ensemble Interpretation

This chapter explores a deterministic hydrodynamically-inspired ensemble interpretation for free relativistic particles, following the original pilot wave theory conceptualized by de Broglie in 1924 and recent advances in hydrodynamic quantum analogs. We couple a one-dimensional periodically forced Klein-Gordon wave equation and a relativistic particle equation of motion, and simulate an ensemble of multiple uncorrelated particle trajectories. The simulations reveal a chaotic particle dynamic behavior, highly sensitive to the initial random condition. Although particles in the simulated ensemble seem to fill out the entire spatiotemporal domain, we find coherent spatiotemporal structures in which particles are less likely to cross. These structures are characterized by de Broglie's wavelength and the relativistic modulation frequency kc. Markedly, the probability density function of the particle ensemble correlates to the square of the absolute wave field, solved here analytically, suggesting a classical deterministic interpretation of de Broglie's matter waves and Born's rule.

quant-ph↗

arXiv2023

Online Learning and Solving Infinite Games with an ERM Oracle

While ERM suffices to attain near-optimal generalization error in the stochastic learning setting, this is not known to be the case in the online learning setting, where algorithms for general concept classes rely on computationally inefficient oracles such as the Standard Optimal Algorithm (SOA). In this work, we propose an algorithm for online binary classification setting that relies solely on ERM oracle calls, and show that it has finite regret in the realizable setting and sublinearly growing regret in the agnostic setting. We bound the regret in terms of the Littlestone and threshold dimensions of the underlying concept class. We obtain similar results for nonparametric games, where the ERM oracle can be interpreted as a best response oracle, finding the best response of a player to a given history of play of the other players. In this setting, we provide learning algorithms that only rely on best response oracles and converge to approximate-minimax equilibria in two-player zero-sum games and approximate coarse correlated equilibria in multi-player general-sum games, as long as the game has a bounded fat-threshold dimension. Our algorithms apply to both binary-valued and real-valued games and can be viewed as providing justification for the wide use of double oracle and multiple oracle algorithms in the practice of solving large games.

cs.LG↗

arXiv2023

Ambient Diffusion: Learning Clean Distributions from Corrupted Data

We present the first diffusion-based framework that can learn an unknown distribution using only highly-corrupted samples. This problem arises in scientific applications where access to uncorrupted samples is impossible or expensive to acquire. Another benefit of our approach is the ability to train generative models that are less likely to memorize individual training samples since they never observe clean training data. Our main idea is to introduce additional measurement distortion during the diffusion process and require the model to predict the original corrupted image from the further corrupted image. We prove that our method leads to models that learn the conditional expectation of the full uncorrupted image given this additional measurement corruption. This holds for any corruption process that satisfies some technical conditions (and in particular includes inpainting and compressed sensing). We train models on standard benchmarks (CelebA, CIFAR-10 and AFHQ) and show that we can learn the distribution even when all the training samples have $90\%$ of their pixels missing. We also show that we can finetune foundation models on small corrupted datasets (e.g. MRI scans with block corruptions) and learn the clean distribution without memorizing the training set.

cs.LG↗

arXiv2023

Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent

Imperfect score-matching leads to a shift between the training and the sampling distribution of diffusion models. Due to the recursive nature of the generation process, errors in previous steps yield sampling iterates that drift away from the training distribution. Yet, the standard training objective via Denoising Score Matching (DSM) is only designed to optimize over non-drifted data. To train on drifted data, we propose to enforce a \emph{consistency} property which states that predictions of the model on its own generated data are consistent across time. Theoretically, we show that if the score is learned perfectly on some non-drifted points (via DSM) and if the consistency property is enforced everywhere, then the score is learned accurately everywhere. Empirically we show that our novel training objective yields state-of-the-art results for conditional and unconditional generation in CIFAR-10 and baseline improvements in AFHQ and FFHQ. We open-source our code and models: https://github.com/giannisdaras/cdm

cs.LG↗

arXiv2022

Learning and Testing Latent-Tree Ising Models Efficiently

We provide time- and sample-efficient algorithms for learning and testing latent-tree Ising models, i.e. Ising models that may only be observed at their leaf nodes. On the learning side, we obtain efficient algorithms for learning a tree-structured Ising model whose leaf node distribution is close in Total Variation Distance, improving on the results of prior work. On the testing side, we provide an efficient algorithm with fewer samples for testing whether two latent-tree Ising models have leaf-node distributions that are close or far in Total Variation distance. We obtain our algorithms by showing novel localization results for the total variation distance between the leaf-node distributions of tree-structured Ising models, in terms of their marginals on pairs of leaves.

cs.LG↗

arXiv2022

EM's Convergence in Gaussian Latent Tree Models

We study the optimization landscape of the log-likelihood function and the convergence of the Expectation-Maximization (EM) algorithm in latent Gaussian tree models, i.e. tree-structured Gaussian graphical models whose leaf nodes are observable and non-leaf nodes are unobservable. We show that the unique non-trivial stationary point of the population log-likelihood is its global maximum, and establish that the expectation-maximization algorithm is guaranteed to converge to it in the single latent variable case. Our results for the landscape of the log-likelihood function in general latent tree models provide support for the extensive practical use of maximum likelihood based-methods in this setting. Our results for the EM algorithm extend an emerging line of work on obtaining global convergence guarantees for this celebrated algorithm. We show our results for the non-trivial stationary points of the log-likelihood by arguing that a certain system of polynomial equations obtained from the EM updates has a unique non-trivial solution. The global convergence of the EM algorithm follows by arguing that all trivial fixed points are higher-order saddle points.

cs.LG↗