Research Papers

arXiv:2510.00526v3 Announce Type: replace-cross Abstract: Supervised fine-tuning (SFT) is the standard approach for post-training large language models (LLMs), yet it often shows limited generalization. We trace this limitation to its default training objective: negative log likelihood (NLL). While NLL is classically optimal when training from scratch, post-training operates in a different paradigm and could violate its optimality assumptions, where models already encode task-relevant priors and supervision can be long and noisy. In this work, we systematically study various probability-based objectives and characterize when and why different objectives succeed or fail under varying conditions. Through comprehensive experiments and extensive ablation studies across 8 model backbones, 27 benchmarks, and 7 domains, we uncover a critical dimension that governs objective behavior: the model-capability continuum. Near the model-strong end, prior-leaning objectives that downweight low-probab

arXiv:2510.04406v2 Announce Type: replace-cross Abstract: Conformal prediction offers finite-sample coverage guarantees under minimal assumptions. However, existing methods treat the entire modeling process as a black box, overlooking opportunities to exploit and understand modular structure. We introduce a conformal prediction framework for two-stage sequential models, where an upstream predictor generates intermediate representations for a downstream model. By decomposing the overall prediction residual into stage-specific components, our method enables practitioners to attribute uncertainty to specific pipeline stages. We develop a risk-controlled parameter selection procedure using family-wise error rate (FWER) control to calibrate stage-wise scaling parameters, and introduce an adaptive extension for non-stationary settings. Experiments on synthetic distribution shifts, as well as real-world supply chain and stock market data, demonstrate that our approach improves coverage under

arXiv:2511.15503v2 Announce Type: replace-cross Abstract: High-performance Host processors can integrate Processing-In-Memory (PIM) devices, which can accelerate memory-intensive kernels of Machine Learning (ML) models, including Large Language Models (LLMs), by leveraging the large memory bandwidth available at PIM cores. However, Host processor needs consecutive elements distributed across DRAM banks, while PIM cores need consecutive elements within their local banks. This necessitates data rearrangements in ML kernel execution that pose significant performance and programmability challenges, further exacerbated by the need to support diverse PIM devices. Current compilation approaches lack systematic optimization for diverse ML kernels and multiple PIM devices, and may largely ignore data rearrangement costs during the compute code optimization step. We show that data rearrangements and compute code optimization are interdependent, and need to be jointly optimized during the tuning

arXiv:2512.15436v2 Announce Type: replace-cross Abstract: We introduce an extension of the partitioned local depth (PaLD) algorithm that is adapted to online applications such as semi-supervised prediction. PaLD is best known for unsupervised, parameter-free clustering, but its robustness is based on triples of data points, making exact analysis computationally expensive. Research is ongoing to improve the scalability of the underlying discrete algorithm and expand the breath of PaLD's applications. The new algorithm we present, online PaLD, is well-suited to situations where it is possible to pre-compute a cohesion network from a reference dataset. After $O(n^3)$ steps to construct a queryable data structure, online PaLD can extend the cohesion network to a new data point in $O(n^2)$ time. Our approach complements previous speed up approaches based on approximation and parallelism. In practical terms, online PaLD makes larger datasets accessible to exact analysis with a relatively sim

arXiv:2601.18685v3 Announce Type: replace-cross Abstract: The capabilities of generative AI in mathematics education are rapidly evolving, posing significant challenges for research to keep pace. Research syntheses remain scarce and risk being outdated by the time of publication. To address this issue, we present a Living Meta-Analysis (LIMA) on the effects of generative AI-based interventions for learning mathematics. Following PRISMA-LSR guidelines, we continuously update the literature base, apply a Bayesian multilevel meta-regression model to account for nested and cumulative data, and publish updated versions on a preprint server at regular intervals. This paper reports results from the third version, including 24 studies, 3 of which were newly included since the second version. The analyses indicate a positive effect (g = 0.40) with a wide credible interval [0.14, 0.67], reflecting the still limited evidence base. Results indicate no publication bias. Moderator analyses indicate

arXiv:2601.22367v2 Announce Type: replace-cross Abstract: Generalized Bayesian Inference (GBI) tempers a loss with a temperature $\beta > 0$ to mitigate overconfidence and improve robustness under model misspecification, but existing GBI methods typically rely on costly MCMC or SDE-based samplers and must be re-run for each new dataset and each $\beta$ value. We give the first fully amortized variational approximation for the tempered posterior family by training a single data- and $\beta$-conditioned neural posterior estimator that enables sampling in a single forward pass, without simulator calls or inference-time MCMC. We introduce two complementary training routes: one synthesizes off-manifold samples from the tempered joint distribution, and the other reweights a fixed base dataset using self-normalized importance sampling (SNIS). We show that the SNIS-weighted objective provides a consistent forward-KL fit to the tempered posterior with finite weight variance. Across four standar

arXiv:2602.08927v3 Announce Type: replace-cross Abstract: We study the problem of online monotone density estimation, where density estimators must be constructed in a predictable manner from sequentially observed data. We propose two online estimators: an online analogue of the classical Grenander estimator, and an expert aggregation estimator inspired by exponential weighting methods from the online learning literature. In the well-specified stochastic setting, where the underlying density is monotone, we show that the expected cumulative log-likelihood gap between the online estimators and the true density admits an $O(n^{1/3})$ bound. We further establish a $\sqrt{n\log{n}}$ pathwise regret bound for the expert aggregation estimator relative to the best offline monotone estimator chosen in hindsight, under minimal regularity assumptions on the observed sequence. As an application of independent interest, we show that the problem of constructing log-optimal p-to-e calibrators for se

arXiv:2602.12534v2 Announce Type: replace-cross Abstract: In truncated linear regression, samples $(x,y)$ are shown only when the outcome $y$ falls inside a certain survival set $S^\star$ and the goal is to estimate the unknown $d$-dimensional regressor $w^\star$. This problem has a long history of study in Statistics and Machine Learning going back to the works of (Galton, 1897; Tobin, 1958) and more recently in, e.g., (Daskalakis et al., 2019; 2021; Lee et al., 2023; 2024). Despite this long history, however, most prior works are limited to the special case where $S^\star$ is precisely known. The more practically relevant case, where $S^\star$ is unknown and must be learned from data, remains open: indeed, here the only available algorithms require strong assumptions on the distribution of the feature vectors (e.g., Gaussianity) and, even then, have a $d^{\mathrm{poly} (1/\varepsilon)}$ run time for achieving $\varepsilon$ accuracy. In this work, we give the first algorithm for trunc

arXiv:2603.04005v2 Announce Type: replace-cross Abstract: The rate-distortion-perception (RDP) tradeoff characterizes the fundamental limits of lossy compression by jointly considering bitrate, reconstruction fidelity, and perceptual quality. While recent neural compression methods have improved perceptual performance, they typically operate at fixed points on the RDP surface, requiring retraining to target different tradeoffs. In this work, we propose a training-free framework that leverages pre-trained diffusion models to traverse the entire RDP surface. Our approach integrates a reverse channel coding (RCC) module with a novel score-scaled probability flow ODE decoder. We theoretically prove that the proposed diffusion decoder is optimal for the distortion-perception tradeoff under AWGN observations and that the overall framework with the RCC module achieves the optimal RDP function in the Gaussian case. Empirical results across multiple datasets demonstrate the framework's flexibil

arXiv:2603.18551v2 Announce Type: replace-cross Abstract: We study how to construct compressed datasets that suffice to recover optimal decisions in linear programs with an unknown cost vector $c$ lying in a prior set $\mathcal{C}$. Recent work by Bennouna et al. provides an exact geometric characterization of sufficient decision datasets (SDDs) via an intrinsic decision-relevant dimension $d^\star$. However, their algorithm for constructing minimum-size SDDs requires solving mixed-integer programs. In this paper, we establish hardness results showing that computing $d^\star$ is NP-hard and deciding whether a dataset is globally sufficient is coNP-hard, thereby resolving a recent open problem posed by Bennouna et al. To address this worst-case intractability, we introduce pointwise sufficiency, a relaxation that requires sufficiency for an individual cost vector. Under nondegeneracy, we provide a polynomial-time cutting-plane algorithm for constructing pointwise-sufficient decision dat

arXiv:2603.24226v3 Announce Type: replace-cross Abstract: Scaling studies for industrial search, advertising, and recommendation have largely emphasized enlarging model capacity or refining architectures. Yet in real-world systems, performance is constrained not only by model size but also by the quality and distribution of training data. Our empirical analysis shows two key bottlenecks: increasing parameters alone yields progressively smaller gains, and the challenges introduced by heterogeneous, large-scale behavior data cannot be fully resolved by architecture tuning in isolation. To address this issue, we present UniScale, a unified framework that couples data scaling with model design. UniScale consists of two components. First, ES$^3$, an entire-space sample construction system, broadens supervision beyond conventional sampled training data by enriching intra-domain search contexts with globally attributed supervisory signals and introducing cross-domain examples that reflect use

arXiv:2604.05129v2 Announce Type: replace-cross Abstract: We investigate the strategic surplus obtainable against a Follow-the-Regularized-Leader (FTRL) learner with constant step size $\eta$ in $n\times m$ two-player zero-sum games played over $T$ rounds against a clairvoyant optimizer. In contrast with prior analysis, we show that the extraction of such regret-scale surplus is an inherent feature of the FTRL family, rather than an artifact of specific instantiations. First, for a fixed max-min optimizer, we establish a sweeping law of order $\Omega(N_{\mathrm{sub}}/\eta)$, proving that utility surplus scales with the number of the learner's suboptimal actions $N$ and vanishes in their absence. Second, for an alternating optimizer, a surplus of $\Omega(\eta T/\mathrm{poly}(n,m))$ can be guaranteed regardless of the equilibrium structure, with high probability, in random games. Our analysis uncovers a sharp geometric dichotomy: non-steep regularizers allow the optimizer to realize the

arXiv:2604.07796v2 Announce Type: replace-cross Abstract: In this paper, we study the problem of mean estimation under 1-bit communication constraints. We propose a novel adaptive mean estimator based solely on randomized threshold queries, where each 1-bit outcome indicates whether a given sample exceeds a sequentially chosen threshold. Our estimator is $(\epsilon, \delta)$-PAC for any distribution with a bounded mean $\mu \in [-\lambda, \lambda]$ and a bounded $k$-th central moment $\mathbb{E}[|X-\mu|^k] \le \sigma^k$ for any fixed $k > 1$. Moreover, our sample complexity is order-optimal in all such tail regimes, i.e., for every such $k$ value. For $k \neq 2$, our estimator's sample complexity matches the unquantized minimax lower bounds plus an unavoidable $O(\log(\lambda/\sigma))$ localization cost. For the finite-variance case ($k=2$), our estimator's sample complexity has an extra multiplicative $O(\log(\sigma/\epsilon))$ penalty, and we establish a novel information-theoretic l

arXiv:2605.10219v2 Announce Type: replace-cross Abstract: We study the parameterized complexity of testing approximate first-order stationarity at a prescribed point for continuous piecewise-affine (PA) functions, a basic task in nonsmooth optimization. PA functions form a canonical model for nonsmooth stationarity testing and capture the local polyhedral geometry that appears in ReLU-type training losses. Recent work by Tian and So (SODA 2025) shows that testing approximate stationarity notions for PA functions is computationally intractable in the worst case, and identifies fixed-dimensional tractability as an open direction. We address this direction from the viewpoint of parameterized complexity, with the ambient dimension $d$ as the parameter. In this paper, we give XP algorithms in fixed dimension for the tractable sides, and prove W[1]-hardness for the complementary sides. Moreover, lower bounds under the Exponential Time Hypothesis rule out algorithms running in time $\rho(d)\s

arXiv:2605.10220v2 Announce Type: replace-cross Abstract: The formation timescale of the Milky Way thick disk is one of the central debates in Galactic archaeology. The age-metallicity relation (AMR), formation timescale, and chemical evolution gradients are frequently used to infer a rapid assembly, short-timescale enrichment, and bursty formation history of the thick disk. However, stellar ages are not directly observable, introducing the potential risk that inferred ages may harbor a systematic compression tied to observational quality. In this paper, we use the same stellar sample and identical physical covariate matching conditions, but two independent age scales--spectroscopic inferred ages (astroNN) and asteroseismic ages (APOKASC-3)--to compare the observable signatures of the thick-disk formation history. We find that several key observables previously supporting a rapid thick-disk formation are systematically weakened under seismic anchoring: the AMR slope flattens from -3.29