A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Self-supervised methods learn from noisy data alone, useful for imaging problems.
It has been noticed that some external CVIs exhibit a preferential bias towards a larger or smaller number of clusters which is monotonic (directly or inversely) in the number of clusters in candidate partitions. This type of bias is caused by the functional form of the CVI model. For example, the popular Rand index (R…
Develops a framework for consistent clustering algorithm benchmarking.
A new method finds DAG models without ground truth.
LLMs fail to match statistical ground truth despite stable run-to-run performance.
Annotating automotive radar data is a difficult task. This article presents an automated way of acquiring data labels which uses a highly accurate and portable global navigation satellite system (GNSS). The proposed system is discussed besides a revision of other label acquisitions techniques and a problem description …
A new method samples from multi-modal distributions without hyperparameter tuning.
Tactile information is important for gripping, stable grasp, and in-hand manipulation, yet the complexity of tactile data prevents widespread use of such sensors. We make use of an unsupervised learning algorithm that transforms the complex tactile data into a compact, latent representation without the need to record g…
A new framework evaluates LLMs by considering judge reliability.
Training autoregressive models to better predict under the test metric, instead of maximizing the likelihood, has been reported to be beneficial in several use cases but brings additional complications, which prevent wider adoption. In this paper, we follow the learning-to-search approach (Daumé III et al., 2009; Leblo…
Effective decision making requires understanding the uncertainty inherent in a prediction. In regression, this uncertainty can be estimated by a variety of methods; however, many of these methods are laborious to tune, generate overconfident uncertainty intervals, or lack sharpness (give imprecise intervals). We addres…
Conformal Alignment ensures trustworthy outputs from foundation models.
Exposure bias refers to the train-test discrepancy that seemingly arises when an autoregressive generative model uses only ground-truth contexts at training time but generated ones at test time. We separate the contributions of the model and the learning framework to clarify the debate on consequences and review propos…
We introduce a novel Deep Learning framework, which quantitatively estimates image segmentation quality without the need for human inspection or labeling. We refer to this method as a Quality Assurance Network -- QANet. Specifically, given an image and a `proposed' corresponding segmentation, obtained by any method inc…
Optical flow refers to the visual motion observed between two consecutive images. Since the degree of freedom is typically much larger than the constraints imposed by the image observations, the straightforward formulation of optical flow as an inverse problem is ill-posed. Standard approaches to determine optical flow…
The rising interest in pattern recognition and data analytics has spurred the development of innovative machine learning algorithms and tools. However, as each algorithm has its strengths and limitations, one is motivated to judiciously fuse multiple algorithms in order to find the "best" performing one, for a given da…
A new method averages neural network parameters to rank features robustly.
Ensemble learning, the machine learning paradigm where multiple algorithms are combined, has exhibited promising perfomance in a variety of tasks. The present work focuses on unsupervised ensemble classification. The term unsupervised refers to the ensemble combiner who has no knowledge of the ground-truth labels that …
With the rapid growth in the number of scientific publications, year after year, it is becoming increasingly difficult to identify quality authoritative work on a single topic. Though there is an availability of scientometric measures which promise to offer a solution to this problem, these measures are mostly quantita…
Universally valid ground truth is almost impossible to obtain or would come at a very high cost. For supervised learning without universally valid ground truth, a recommended approach is applying crowdsourcing: Gathering a large data set annotated by multiple individuals of varying possibly expertise levels and inferri…
Paper proposes a method to recover accurate labels from partially valid data in multi-label learning.
Tests for classifier independence without ground truth labels.
Paper proposes a CNN-based method for estimating intra frame bits and quality.
Continuous monitoring of cardiac health under free living condition is crucial to provide effective care for patients undergoing post operative recovery and individuals with high cardiac risk like the elderly. Capacitive Electrocardiogram (cECG) is one such technology which allows comfortable and long term monitoring t…
RealCause provides a realistic benchmark for causal inference.
PDO optimizes LLM prompts without labels, improving performance.
We propose an iterative scheme for feature-based positioning using a new weighted dissimilarity measure with the goal of reducing the impact of large errors among the measured or modeled features. The weights are computed from the location-dependent standard deviations of the features and stored as part of the referenc…
Recently developed deep-learning-based denoisers often outperform state-of-the-art conventional denoisers such as the BM3D. They are typically trained to minimize the mean squared error (MSE) between the output image of a deep neural network (DNN) and a ground truth image. Thus, it is important for deep-learning-based …
Estimates classifier errors without ground truth using algebraic geometry.
Ranking a set of objects involves establishing an order allowing for comparisons between any pair of objects in the set. Oftentimes, due to the unavailability of a ground truth of ranked orders, researchers resort to obtaining judgments from multiple annotators followed by inferring the ground truth based on the collec…
Paper introduces metrics to evaluate missing data imputation without ground truth.
Improved forecasting in daily time series competition using a correlator method.
A new score measures data reliability without ground truth.
QUACKIE creates a new benchmark for NLP interpretability.
Unsupervised clustering can reproduce categorization systems if features and metrics are correctly selected.
This paper proposes a set of criteria to evaluate the objectiveness of explanation methods of neural networks, which is crucial for the development of explainable AI, but it also presents significant challenges. The core challenge is that people usually cannot obtain ground-truth explanations of the neural network. To …
New method accounts for uncertainty in medical AI evaluations.
Generative model combines multi-dimensional annotations for more accurate ground truth estimation.
New method falsifies causal discovery results without ground truth.
This work optimizes signal estimation for sparse MRA with collision-free signals.
SAMPLR optimizes for ground truth in aleatoric parameters to avoid curriculum-induced covariate shift.
Autonomy and adaptation of machines requires that they be able to measure their own errors. We consider the advantages and limitations of such an approach when a machine has to measure the error in a regression task. How can a machine measure the error of regression sub-components when it does not have the ground truth…
BoostMD accelerates molecular dynamics simulations by 8x with ML force fields.
We address the problem of vehicle self-localization from multi-modal sensor information and a reference map. The map is generated off-line by extracting landmarks from the vehicle's field of view, while the measurements are collected similarly on the fly. Our goal is to determine the autonomous vehicle's pose from the …
Latent truth discovery, LTD for short, refers to the problem of aggregating ltiple claims from various sources in order to estimate the plausibility of atements about entities. In the absence of a ground truth, this problem is highly challenging, when some sources provide conflicting claims and others no claims at all.…
Preconditioned SGD accelerates convergence for ill-conditioned huge-scale matrix completion.
Study reveals issues with neural autoregressive models and proposes mode recovery cost.
It is widely believed that sharing gradients will not leak private training data in distributed learning systems such as Collaborative Learning and Federated Learning, etc. Recently, Zhu et al. presented an approach which shows the possibility to obtain private training data from the publicly shared gradients. In their…