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.
The paper uses geometry to understand how neural networks learn.
RLVR maintains safety while improving reasoning capabilities in LLMs.
The study uncovers latent capabilities of language models via causal representation learning.
A new framework ensures model safety by retaining old model capabilities while improving new tasks.
When building a unified vision system or gradually adding new capabilities to a system, the usual assumption is that training data for all tasks is always available. However, as the number of tasks grows, storing and retraining on such data becomes infeasible. A new problem arises where we add new capabilities to a Con…
New framework transfers latent knowledge from weak to strong models.
Paper examines LLM capability benchmarks through construct validity, favoring nomological account.
Bio-inspired neuromorphic hardware is a research direction to approach brain's computational power and energy efficiency. Spiking neural networks (SNN) encode information as sparsely distributed spike trains and employ spike-timing-dependent plasticity (STDP) mechanism for learning. Existing hardware implementations of…
Transformers can scale both context and task, but MLPs can only scale task.
Layout design with complex constraints is a challenging problem to solve due to the non-uniqueness of the solution and the difficulties in incorporating the constraints into the conventional optimization-based methods. In this paper, we propose a design method based on the recently developed machine learning technique,…
A new method learns complex dynamical systems from data efficiently.
Transformers learn to play games in-context, proving Nash equilibrium.
HeteroFL trains diverse clients with varying capabilities efficiently.
ML Compass helps organizations choose AI models that balance utility, cost, and compliance.
Information-theoretic bounded rationality describes utility-optimizing decision-makers whose limited information-processing capabilities are formalized by information constraints. One of the consequences of bounded rationality is that resource-limited decision-makers can join together to solve decision-making problems …
We evaluate the distribution learning capabilities of generative adversarial networks by testing them on synthetic datasets. The datasets include common distributions of points in space and images containing polygons of various shapes and sizes. We find that by and large GANs fail to faithfully recreate point dat…
A meta-learning method learns adaptive robust loss functions for noisy labels.
Using variational Bayes neural networks, we develop an algorithm capable of accumulating knowledge into a prior from multiple different tasks. The result is a rich and meaningful prior capable of few-shot learning on new tasks. The posterior can go beyond the mean field approximation and yields good uncertainty on the …
Transformers solve Gaussian Mixture Models without supervision.
AI advances impact asset management, offering new decision-making capabilities.
Bayesian framework for sequential learning tasks with low-rank approximations.
Wind energy forecasting helps to manage power production, and hence, reduces energy cost. Deep Neural Networks (DNN) mimics hierarchical learning in the human brain and thus possesses hierarchical, distributed, and multi-task learning capabilities. Based on aforementioned characteristics, we report Deep Belief Network …
Music Inpainting is the task of filling in missing or lost information in a piece of music. We investigate this task from an interactive music creation perspective. To this end, a novel deep learning-based approach for musical score inpainting is proposed. The designed model takes both past and future musical context i…
We present Manifold Alignment Determination (MAD), an algorithm for learning alignments between data points from multiple views or modalities. The approach is capable of learning correspondences between views as well as correspondences between individual data-points. The proposed method requires only a few aligned exam…
Fine-tuning LLMs improves capability but harms safety, study finds.
Proposes a framework to identify and correct model-form errors in nonlinear systems.
Performing supervised learning from the data synthesized by using Generative Adversarial Networks (GANs), dubbed GAN-synthetic data, has two important applications. First, GANs may generate more labeled training data, which may help improve classification accuracy. Second, in scenarios where real data cannot be release…
With few exceptions, the field of Machine Learning (ML) research has largely ignored the browser as a computational engine. Beyond an educational resource for ML, the browser has vast potential to not only improve the state-of-the-art in ML research, but also, inexpensively and on a massive scale, to bring sophisticate…
Variational autoencoders (VAEs) are widely used deep generative models capable of learning unsupervised latent representations of data. Such representations are often difficult to interpret or control. We consider the problem of unsupervised learning of features correlated to specific labels in a dataset. We propose a …
Deep learning methods are often difficult to apply in the legal domain due to the large amount of labeled data required by deep learning methods. A recent new trend in the deep learning community is the application of multi-task models that enable single deep neural networks to perform more than one task at the same ti…
Chronos-2 forecasts multivariate and covariate data without task-specific training.
Study uses machine learning to predict nonlinear seismic brace behavior.
New approach extracts AI model representations for steering and monitoring.
This paper shows ARMs and EBMs are equivalent, revealing ARM lookahead capabilities.
This paper presents the Variation Network (VarNet), a generative model providing means to manipulate the high-level attributes of a given input. The originality of our approach is that VarNet is not only capable of handling pre-defined attributes but can also learn the relevant attributes of the dataset by itself. Thes…
Paper proposes a new financial fraud detection system using improved RF and GBM.
Robotic table tennis learns efficient policies to return balls at 100Hz.
Deep Reinforcement Learning (DRL) has emerged as a powerful control technique in robotic science. In contrast to control theory, DRL is more robust in the thorough exploration of the environment. This capability of DRL generates more human-like behaviour and intelligence when applied to the robots. To explore this capa…
Bayesian deep learning improves deep learning's capabilities across diverse settings.
Designing a deep neural network (DNN) with good generalization capability is a complex process especially when the weights are severely quantized. Model averaging is a promising approach for achieving the good generalization capability of DNNs, especially when the loss surface for training contains many sharp minima. W…
Recurrent neural networks (RNNs) are powerful constructs capable of modeling complex systems, up to and including Turing Machines. However, learning such complex models from finite training sets can be difficult. In this paper we empirically show that RNNs can learn models of computer peripheral devices through input a…
Study shows how a strong model can learn a task's feature while retaining other capabilities.
A new semi-supervised ensemble algorithm called XGBOD (Extreme Gradient Boosting Outlier Detection) is proposed, described and demonstrated for the enhanced detection of outliers from normal observations in various practical datasets. The proposed framework combines the strengths of both supervised and unsupervised mac…
The security of Deep Reinforcement Learning (Deep RL) algorithms deployed in real life applications are of a primary concern. In particular, the robustness of RL agents in cyber-physical systems against adversarial attacks are especially vital since the cost of a malevolent intrusions can be extremely high. Studies hav…
New model predicts particle precipitation from magnetosphere to ionosphere.
In this work we describe a novel deep reinforcement learning architecture that allows multiple actions to be selected at every time-step in an efficient manner. Multi-action policies allow complex behaviours to be learnt that would otherwise be hard to achieve when using single action selection techniques. We use both …
Deep RL optimizes sensor placement in digital twins for dynamic data acquisition.
Research into automated systems for detecting and classifying marine mammals in acoustic recordings is expanding internationally due to the necessity to analyze large collections of data for conservation purposes. In this work, we present a Convolutional Neural Network that is capable of classifying the vocalizations o…