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.
Paper introduces efficient top-k selection with differential privacy.
Enhances deep learning models to resist adversarial attacks.
A hybrid neural network improves robustness in estimating vehicle parameters from noisy data.
Develops NPMC method for noisy labels, improving multiclass classification accuracy.
Framework uses diffusion models to infer material properties from noisy mechanical measurements.
Method identifies root causes of anomalies in causal processes.
Paper proposes a novel model to improve n-ary cross-sentence relation extraction by addressing noisy data and non-consecutive sentences.
We consider the problem of Probably Approximate Correct (PAC) learning of a binary classifier from noisy labeled examples acquired from multiple annotators (each characterized by a respective classification noise rate). First, we consider the complete information scenario, where the learner knows the noise rates of all…
Node-perturbation learning is a type of statistical gradient descent algorithm that can be applied to problems where the objective function is not explicitly formulated, including reinforcement learning. It estimates the gradient of an objective function by using the change in the object function in response to the per…
New method improves few-shot learning with noisy labels.
Noisy Max and Sparse Vector are selection algorithms for differential privacy and serve as building blocks for more complex algorithms. In this paper we show that both algorithms can release additional information for free (i.e., at no additional privacy cost). Noisy Max is used to return the approximate maximizer amon…
Quantum tech speeds up financial risk assessment.
Method counters noisy labels by discounting distant samples.
INGB improves oversampling for noisy imbalanced datasets.
Many privacy mechanisms reveal high-level information about a data distribution through noisy measurements. It is common to use this information to estimate the answers to new queries. In this work, we provide an approach to solve this estimation problem efficiently using graphical models, which is particularly effecti…
A fundamental result in differential privacy states that the privacy guarantees of a mechanism are preserved by any post-processing of its output. In this paper we investigate under what conditions stochastic post-processing can amplify the privacy of a mechanism. By interpreting post-processing as the application of a…
Improved graph attention model for noisy graphs.
Deep neural networks can generalize well even with perfect fits to noisy data.
QA-Token improves tokenization for noisy data, boosting model performance.
Study real-world noisy labels from human annotations for better understanding.
We study reinforcement learning of chatbots with recurrent neural network architectures when the rewards are noisy and expensive to obtain. For instance, a chatbot used in automated customer service support can be scored by quality assurance agents, but this process can be expensive, time consuming and noisy. Previous …
Study neural networks learning from noisy examples via reverberation.
The rapid adoption of machine learning has increased concerns about the privacy implications of machine learning models trained on sensitive data, such as medical records or other personal information. To address those concerns, one promising approach is Private Aggregation of Teacher Ensembles, or PATE, which transfer…
Enhances privacy in machine learning through Rényi Pufferfish mechanisms.
Study shows optimal self-distillation improves model performance on noisy data.
Paper introduces Isotonic Mechanism for better item scoring.
Over-parameterized models can memorize noisy labels and still generalize well, revealing a hidden structure.
In this paper we are interested in the prediction of preterm birth based on diagnosis codes from longitudinal EHR. We formulate the prediction problem as a supervised classification with noisy labels. Our base classifier is a Recurrent Neural Network with an attention mechanism. We assume the availability of a data sub…
Capturing the microscopic interactions that determine molecular reactivity poses a challenge across the physical sciences. Even a basic understanding of the underlying reaction mechanisms can substantially accelerate materials and compound design, including the development of new catalysts or drugs. Given the difficult…
Several data analysis techniques employ similarity relationships between data points to uncover the intrinsic dimension and geometric structure of the underlying data-generating mechanism. In this paper we work under the model assumption that the data is made of random perturbations of feature vectors lying on a low-di…
This work proposes a new method for simultaneous probabilistic identification and control of an observable, fully-actuated mechanical system. Identification is achieved by conditioning stochastic process priors on observations of configurations and noisy estimates of configuration derivatives. In contrast to previous w…
A two-stage optimization framework reduces label noise in federated learning.
Gaussian process model learns Hamiltonian systems from noisy data.
Paper tackles noisy labels by compressing feature representations.
Enhances AI models with human feedback for noisy data.
Study on SignGD optimization of two-layer transformer on noisy data.
We investigate the problem of learning discrete, undirected graphical models in a differentially private way. We show that the approach of releasing noisy sufficient statistics using the Laplace mechanism achieves a good trade-off between privacy, utility, and practicality. A naive learning algorithm that uses the nois…
In reinforcement learning algorithms, leveraging multiple views of the environment can improve the learning of complicated policies. In multi-view environments, due to the fact that the views may frequently suffer from partial observability, their level of importance are often different. In this paper, we propose a dee…
Large datasets often have unreliable labels-such as those obtained from Amazon's Mechanical Turk or social media platforms-and classifiers trained on mislabeled datasets often exhibit poor performance. We present a simple, effective technique for accounting for label noise when training deep neural networks. We augment…
The paper analyzes network models with binary values and sub-Gamma noise, deriving asymptotic properties.
Unified Bayesian framework for uncertainty quantification in mechanics.
Data is continuously generated by modern data sources, and a recent challenge in machine learning has been to develop techniques that perform well in an incremental (streaming) setting. In this paper, we investigate the problem of private machine learning, where as common in practice, the data is not given at once, but…
Paper presents an efficient algorithm for estimating Lipschitz functions from noisy data.
In this work, we provide a new formulation for Graph Convolutional Neural Networks (GCNNs) for link prediction on graph data that addresses common challenges for biomedical knowledge graphs (KGs). We introduce a regularized attention mechanism to GCNNs that not only improves performance on clean datasets, but also favo…
Study improves KRR for non-i.i.d. data, with applications in denoising.
New algorithm improves multitask learning across diverse agents.
We present a detailed analysis of the self-organization phenomenon in which the stylized facts originate from finite size effects with respect to the number of agents considered and disappear in the limit of an infinite population. By introducing the possibility that agents can enter or leave the market depending on th…
We consider the problem of training a model under the presence of label noise. Current approaches identify samples with potentially incorrect labels and reduce their influence on the learning process by either assigning lower weights to them or completely removing them from the training set. In the first case the model…