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.
Large deviation principle for deep neural networks with ReLU activation.
This paper studies activation sparsity in large language models, finding key trends and implications.
Active testing for large language models is made more efficient and accurate.
A new method improves active learning for large batch sizes.
Paper proposes a new activation function to reduce overfitting and large weight update issues.
Using more than 6.7 billions of trades, we explore how the tick-by-tick dynamics of limit order books depends on the aggregate actions of large investment funds on a much larger (quarterly) timescale. In particular, we find that the well-established long memory of market order signs is markedly weaker when large invest…
A new framework scales active search for large datasets.
Deep learning models can overfit noisy data without losing generalization.
Efficiently selects nearest neighbors for labeling to speed up active learning.
S2D selectively decays large singular values to improve quantization of neural activations.
We propose a new batch mode active learning algorithm designed for neural networks and large query batch sizes. The method, Discriminative Active Learning (DAL), poses active learning as a binary classification task, attempting to choose examples to label in such a way as to make the labeled set and the unlabeled pool …
Active testing reduces label costs for efficient model evaluation.
Annotating the right data for training deep neural networks is an important challenge. Active learning using uncertainty estimates from Bayesian Neural Networks (BNNs) could provide an effective solution to this. Despite being theoretically principled, BNNs require approximations to be applied to large-scale problems, …
Convolutional neural networks (CNNs) have been successfully applied to many recognition and learning tasks using a universal recipe; training a deep model on a very large dataset of supervised examples. However, this approach is rather restrictive in practice since collecting a large set of labeled images is very expen…
FAQ efficiently evaluates LLMs with statistical guarantees using adaptive query selection.
IMPACT optimizes LLM compression by focusing on activation importance, reducing model size up to 55.4%.
New algorithms speed up learning from large screens of proteins.
Bal-PM reduces preference labeling costs for LLMs.
Manually labelling large collections of text data is a time-consuming, expensive, and laborious task, but one that is necessary to support machine learning based on text datasets. Active learning has been shown to be an effective way to alleviate some of the effort required in utilising large collections of unlabelled …
A new algorithm improves efficiency in selecting examples for deep learning.
Leveraging the wealth of unlabeled data produced in recent years provides great potential for improving supervised models. When the cost of acquiring labels is high, probabilistic active learning methods can be used to greedily select the most informative data points to be labeled. However, for many large-scale problem…
Token-adaptive FFN design improves LLM expressivity.
We study layered neural networks of rectified linear units (ReLU) in a modelling framework for stochastic training processes. The comparison with sigmoidal activation functions is in the center of interest. We compute typical learning curves for shallow networks with K hidden units in matching student teacher scenarios…
Improves decentralized learning by teleporting active nodes for better convergence.
It is well-known that overparametrized neural networks trained using gradient-based methods quickly achieve small training error with appropriate hyperparameter settings. Recent papers have proved this statement theoretically for highly overparametrized networks under reasonable assumptions. These results either assume…
Neural networks learn distance-based representations, not just intensity.
In the world of big data, large but costly to label datasets dominate many fields. Active learning, a semi-supervised alternative to the standard PAC-learning model, was introduced to explore whether adaptive labeling could learn concepts with exponentially fewer labeled samples. While previous results show that active…
Several recent papers investigate Active Learning (AL) for mitigating the data dependence of deep learning for natural language processing. However, the applicability of AL to real-world problems remains an open question. While in supervised learning, practitioners can try many different methods, evaluating each agains…
Improved EXACT strategy reduces GNN memory consumption and runtime.
Paper proposes efficient RLHF methods for LLMs using active queries.
Wide networks with polynomial activations have proven asymptotic behavior.
There has been a growing interest in expressivity of deep neural networks. However, most of the existing work about this topic focuses only on the specific activation function such as ReLU or sigmoid. In this paper, we investigate the approximation ability of deep neural networks with a broad class of activation functi…
Recent work by Brock et al. (2018) suggests that Generative Adversarial Networks (GANs) benefit disproportionately from large mini-batch sizes. Unfortunately, using large batches is slow and expensive on conventional hardware. Thus, it would be nice if we could generate batches that were effectively large though actual…
Mean field theory has been successfully used to analyze deep neural networks (DNN) in the infinite size limit. Given the finite size of realistic DNN, we utilize the large deviation theory and path integral analysis to study the deviation of functions represented by DNN from their typical mean field solutions. The para…
Active learning from demonstration allows a robot to query a human for specific types of input to achieve efficient learning. Existing work has explored a variety of active query strategies; however, to our knowledge, none of these strategies directly minimize the performance risk of the policy the robot is learning. U…
Active-GRPO improves molecular optimization by actively deciding when to imitate or self-improve.
The choice of activation function can have a large effect on the performance of a neural network. While there have been some attempts to hand-engineer novel activation functions, the Rectified Linear Unit (ReLU) remains the most commonly-used in practice. This paper shows that evolutionary algorithms can discover novel…
Learning the activities of animals is important for the purpose of monitoring their welfare vis a vis their behaviour with respect to their environment and conspecifics. While previous works have largely focused on activity recognition in a single animal, little or no work has been done in learning the collective behav…
ZDP detects drift in large language models without labels, proving key theorems and metrics.
Interactive machine learning improves learning efficiency with user input.
This paper proposes an improved active learning method using classification trees.
The problem of active diagnosis arises in several applications such as disease diagnosis, and fault diagnosis in computer networks, where the goal is to rapidly identify the binary states of a set of objects (e.g., faulty or working) by sequentially selecting, and observing, (noisy) responses to binary valued queries. …
Learning automatically the best activation function for the task is an active topic in neural network research. At the moment, despite promising results, it is still difficult to determine a method for learning an activation function that is at the same time theoretically simple and easy to implement. Moreover, most of…
Active learning reduces smart meter data needs for better electric load predictions.
Enhanced network threat detection using KG, LLM, and imbalanced learning.
Active learning selects samples for labeling to build accurate models with minimal labeled data.
Active sampling improves design space exploration for analog circuits.
New framework improves fairness in small data settings.