arXiv research

Polynomial-time tester-learner for general halfspaces with Gaussian adversarial noise.

New approach for testable learning using moment matching and Rademacher complexity.

A new calibration metric bridges testability and actionability.

Local learning method selects covariates for causal effect estimation in the presence of latent variables.

Efficient algorithm for learning halfspaces in a new model with polynomial time complexity.

Understanding statistical inference under possibly non-sparse high-dimensional models has gained much interest recently. For a given component of the regression coefficient, we show that the difficulty of the problem depends on the sparsity of the corresponding row of the precision matrix of the covariates, not the spa…

Polynomial-time algorithm for learning halfspaces with Gaussian-distributed data and adversarial noise.

New calibration measure SCDL improves trust in AI predictions.

We introduce the hemicubic codes, a family of quantum codes obtained by associating qubits with the $p$-faces of the $n$-cube (for $n>p$) and stabilizer constraints with faces of dimension $(p\pm1)$. The quantum code obtained by identifying antipodal faces of the resulting complex encodes one logical qubit into $N = 2^…

Detect hidden confounding in observational data using multiple environments.

This paper studies structure detection problems in high temperature ferromagnetic (positive interaction only) Ising models. The goal is to distinguish whether the underlying graph is empty, i.e., the model consists of independent Rademacher variables, versus the alternative that the underlying graph contains a subgraph…

Identifying components and estimating mixing weights in unlabeled finite mixtures under marginal independence.

Significant pattern mining, the problem of finding itemsets that are significantly enriched in one class of objects, is statistically challenging, as the large space of candidate patterns leads to an enormous multiple testing problem. Recently, the concept of testability was proposed as one approach to correct for mult…

We propose a method to learn causal response representations through direct effect analysis.

New method estimates causal effects without knowing graph structure.

The paper introduces tests for missing data models based on graph assumptions.

New theory for local parameterization of deep ReLU networks.

A new approach to learning in brain-like networks using adversarial algorithms.

The estimation of treatment effects is a pervasive problem in medicine. Existing methods for estimating treatment effects from longitudinal observational data assume that there are no hidden confounders, an assumption that is not testable in practice and, if it does not hold, leads to biased estimates. In this paper, w…

Universal tester-learner for halfspaces over structured distributions.

Probabilistic graphical models (PGMs) have become a popular tool for computational analysis of biological data in a variety of domains. But, what exactly are they and how do they work? How can we use PGMs to discover patterns that are biologically relevant? And to what extent can PGMs help us formulate new hypotheses t…

Reinforcement learning (RL) tasks are challenging to implement, execute and test due to algorithmic instability, hyper-parameter sensitivity, and heterogeneous distributed communication patterns. We argue for the separation of logical component composition, backend graph definition, and distributed execution. To this e…

We study random 2-dimensional complexes in the Linial - Meshulam model and find torsion in their fundamental groups at various regimes. We find a simple algorithmically testable criterion for a subcomplex of a random 2-complex to be aspherical; this implies that any aspherical subcomplex of a random 2-complex satisfies…

Tests whether a treatment's effect is fully mediated by observed outcomes and identifies causal mechanisms.

The semantic map calibrates uncertainty from language model probabilities.

Finding statistically significant interactions between binary variables is computationally and statistically challenging in high-dimensional settings, due to the combinatorial explosion in the number of hypotheses. Terada et al. recently showed how to elegantly address this multiple testing problem by excluding non-tes…

A new framework for adaptive behavior using reusable value profiles.

We use standard physics techniques to model trading and price formation in a market under the assumption that order arrival and cancellations are Poisson random processes. This model makes testable predictions for the most basic properties of a market, such as the diffusion rate of prices, which is the standard measure…

Representation and learning of long-range dependencies is a central challenge confronted in modern applications of machine learning to sequence data. Yet despite the prominence of this issue, the basic problem of measuring long-range dependence, either in a given data source or as represented in a trained deep model, r…

Many research fields codify their findings in standard formats, often by reporting correlations between quantities of interest. But the space of all testable correlates is far larger than scientific resources can currently address, so the ability to accurately predict correlations would be useful to plan research and a…

New framework explains adversarial examples in neural nets.

Criteria for extending degree-2 Azumaya algebras with C2-actions over curves.

The literature on structured prediction for NLP describes a rich collection of distributions and algorithms over sequences, segmentations, alignments, and trees; however, these algorithms are difficult to utilize in deep learning frameworks. We introduce Torch-Struct, a library for structured prediction designed to tak…

As machine learning algorithms are increasingly applied to high impact yet high risk tasks, such as medical diagnosis or autonomous driving, it is critical that researchers can explain how such algorithms arrived at their predictions. In recent years, a number of image saliency methods have been developed to summarize …

AI systems need reliable testing to ensure safety and trustworthiness.

ZDP detects drift in large language models without labels, proving key theorems and metrics.

We provide a microfoundation for linear price impact models in a stationary market.

New method identifies whether equity return predictability is due to magnitude shrinkage or directional reversal.

Traditional anatomical analyses captured only a fraction of real phenomic information. Here, we apply deep learning to quantify total phenotypic similarity across 2468 butterfly photographs, covering 38 subspecies from the polymorphic mimicry complex of $\textit{Heliconius erato}$ and $\textit{Heliconius melpomene}$. E…

Increasing the batch size is a popular way to speed up neural network training, but beyond some critical batch size, larger batch sizes yield diminishing returns. In this work, we study how the critical batch size changes based on properties of the optimization algorithm, including acceleration and preconditioning, thr…

Generative model solves financial market equilibria with stable reinforcement learning.

NFT royalties boost creator earnings by sharing risk, reducing info asymmetry, and enabling price discrimination.

The two-dimensional renormalization group acting as the Ricci flow $Λ\frac{\partial}{\partialΛ} g_{μν} = R_{μν}$ produces a specific 1+3 dimensional space-time metric which describes an expanding universe that starts with a big bang $a \sim t^{\scriptscriptstyle 1/\sqrt3}$ then decelerates until $z=0.2$ then accelerate…

The paper clarifies the approximation of SGD with Ito SDEs for finite learning rates.

We develop a theory for the market impact of large trading orders, which we call metaorders because they are typically split into small pieces and executed incrementally. Market impact is empirically observed to be a concave function of metaorder size, i.e., the impact per share of large metaorders is smaller than that…

Synthesizes computational approaches to understand neural timescales.

Estimating the capabilities, or inputs of production, that drive and constrain the economic development of urban areas has remained a challenging goal. We posit that capabilities are instantiated in the complexity and sophistication of urban activities, the knowhow of individual workers, and the city-wide collective kn…

New method discovers context effects in choice data.