MLINFO COLLECTION
We consider the problem of online linear classification, where a stream of unlabeled samples is available, and annotation is costly. We investigate the optimal query policy, that prescribes whether…
Can algorithms be learned and evolved as models, rather than repeatedly redesigned as programs? We explore this question by introducing Algorithm Modelization, a new paradigm that turns iterative…
Conformal test martingales (CTMs) are e-processes for sequentially testing exchangeability via p-values produced by a conformity function $A$. However, any distribution shift that preserves the…
Digital marketplaces increasingly earn revenue from transaction commissions and seller-facing data services. Sellers may purchase data to increase revenue or avoid competing with an informed rival.
Training language agents is bottlenecked by the high cost of long-horizon rollouts, yet standard agentic reinforcement learning (RL) learns only from a terminal scalar reward, leaving the supervision…
Indivisible resources allocated in advance may need to be reallocated when capacity reductions make existing assignments infeasible, yet monetary compensation is often impractical or undesirable. We…
Advanced persistent threats (APTs) are a major concern in federated learning (FL) deployments in critical sectors such as healthcare, and finance. Traditional defense mechanisms fail to contain APTs…
Inferring dynamics from real-world experimental data is inherently ambiguous, as many plausible dynamical systems can explain the same positional observations at measurement times. For higher…
The input space of single-spike neural networks decomposes into causal pieces, and the number of causal pieces has been shown to provide a lower bound on the approximation error for some spiking…
We study how to evaluate $K$ target policies simultaneously in stochastic contextual bandits with linear reward structure. Given a known $d$-dimensional feature map and reward-free access to policy…
Solving imperfect-information games at scale rests on counterfactual regret minimization with the regret matching$^{+}$ (RM$^{+}$) update, and a seemingly minor implementation choice accounts for…
Many modern learning systems are used not to select a single best action, but to sample diverse high-quality outputs. Examples include entropy-regularized reinforcement learning, RLHF, and…
Robust covariance estimation under entry-wise contamination and missing data is challenging in various signal processing applications. Under the Student-$t$ model, observation-level reweighting…
Flow matching has emerged as a powerful generative family for simulation-based inference (SBI). However, sampling and density evaluation require numerical integration at inference time.
To facilitate the solving of complex problems, evolutionary multitask optimization is regarded as a promising technique due to its capacity for cross-task knowledge transfer. In contrast to empirical…
Iterative sampling in diffusion models can lead to error accumulation due to exposure bias. The denoiser is trained on real images interpolated with noise, but at inference its inputs are constructed…
Spiking neural networks (SNNs) have increasingly incorporated rich neuronal dynamics to enhance temporal processing. However, richer dynamics do not necessarily enable neurons to adapt how…
Engineering design tools increasingly embed optimizers as ready-made components that users select by algorithm name, while operator settings and bound, integer and duplicate handling stay fixed…
Pairwise comparison data are a standard supervision signal in preference learning, but disagreement in such data can reflect stable latent heterogeneity, ephemeral stochasticity, or non-binary…
In a repeated Stackelberg security game, a defender commits in every round to a randomized allocation of its resources, and an attacker, drawn from a set of types, best-responds. Existing no-regret…
We resolve the problem of unweighted online stochastic matching with a known arrival law by establishing its optimal competitive ratio. For Poisson arrivals, we achieve $1-e/e^e\approx0.8206$,…
Exploiting temporal information in datasets with high temporal dependencies (such as spoken keyword recognition) by spiking models is still an open problem. Promising frameworks include Time-To-First…
The ability to represent temporal information is often hypothesized to underlie the efficiency and learning capabilities of biological neural networks. This motivates the development of spiking…
We prove that computing a complete contiguous $\varepsilon$-envy-free cake allocation is PPAD-complete for normalized rational piecewise-constant additive valuations. The hardness holds even when…