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.
Active-GRPO improves molecular optimization by actively deciding when to imitate or self-improve.
LASER compresses recursive model activations by exploiting their low-dimensional structure.
Active learning holds promise of significantly reducing data annotation costs while maintaining reasonable model performance. However, it requires sending data to annotators for labeling. This presents a possible privacy leak when the training set includes sensitive user data. In this paper, we describe an approach for…
uGMM-NN integrates probabilistic reasoning into neural networks.
Active inference selects actions to maximize information gain, aiding structure learning.
The paper explores how to evaluate Bayesian approximations in neural networks.
The uninformative ordering of artificial neurons in Deep Neural Networks complicates visualizing activations in deeper layers. This is one reason why the internal structure of such models is very unintuitive. In neuroscience, activity of real brains can be visualized by highlighting active regions. Inspired by those te…
DFRot improves LLMs by reducing outlier and massive activation effects.
Bayesian optimization improves policy search in reinforcement learning.
We extend Kirman's model by introducing variable event time scale. The proposed flexible time scale is equivalent to the variable trading activity observed in financial markets. Stochastic version of the extended Kirman's agent based model is compared to the non-linear stochastic models of long-range memory in financia…
This paper expresses the structure of artificial neural network (ANN) as a functional form, using the activation integral concept derived from the activation function. In this way, the structure of ANN can be represented by a simple function, and it is possible to find the mathematical solutions of ANN. Thus, it can be…
ABCI infers causal models and queries simultaneously using Bayesian active learning.
A new method normalizes activations to match batch normalization without batch dependence.
Survey of neurosymbolic AI methods for reasoning over knowledge graphs.
Sigmoid-type networks avoid vanishing gradients with regularization and rescaling.
Alpha-R1 uses LLMs to reason about economic factors and news for better alpha screening.
Active learning agents typically employ a query selection algorithm which solely considers the agent's learning objectives. However, this may be insufficient in more realistic human domains. This work uses imitation learning to enable an agent in a constrained environment to concurrently reason about both its internal …
We propose an active set selection framework for Gaussian process classification for cases when the dataset is large enough to render its inference prohibitive. Our scheme consists of a two step alternating procedure of active set update rules and hyperparameter optimization based upon marginal likelihood maximization.…
Adaptive Nucleus Truncation Improves Long-Form Reasoning
In this work we investigate the reasons why Batch Normalization (BN) improves the generalization performance of deep networks. We argue that one major reason, distinguishing it from data-independent normalization methods, is randomness of batch statistics. This randomness appears in the parameters rather than in activa…
As Computer Vision moves from a passive analysis of pixels to active analysis of semantics, the breadth of information algorithms need to reason over has expanded significantly. One of the key challenges in this vein is the ability to identify the information required to make a decision, and select an action that will …
Until recently, research on artificial neural networks was largely restricted to systems with only two types of variable: Neural activities that represent the current or recent input and weights that learn to capture regularities among inputs, outputs and payoffs. There is no good reason for this restriction. Synapses …
Deep neural networks (DNN) are able to successfully process and classify speech utterances. However, understanding the reason behind a classification by DNN is difficult. One such debugging method used with image classification DNNs is activation maximization, which generates example-images that are classified as one o…
Bayesian model predicts online activity participation.
MACC learns communication protocols by adapting counterfactual reasoning.
AI uses KGs to assess economic impact of selective lockdowns on Italian companies.
Study shows big winner stocks significantly impact passive and active investment strategies.
A wide variety of activation functions have been proposed for neural networks. The Rectified Linear Unit (ReLU) is especially popular today. There are many practical reasons that motivate the use of the ReLU. This paper provides new theoretical characterizations that support the use of the ReLU, its variants such as th…
Strict partial order is a mathematical structure commonly seen in relational data. One obstacle to extracting such type of relations at scale is the lack of large-scale labels for building effective data-driven solutions. We develop an active learning framework for mining such relations subject to a strict order. Our a…
Agents learn state ambiguity from non-linear sensor data using Gaussian approximations.
Active learning (AL) is a learning paradigm where an active learner has to train a model (e.g., a classifier) which is in principal trained in a supervised way, but in AL it has to be done by means of a data set with initially unlabeled samples. To get labels for these samples, the active learner has to ask an oracle (…
A2MT learns agents to select which modalities to acquire at test time.
Theory of MoE Transformers' generalization and scaling.
Predicting and improving player retention is crucial to the success of mobile Free-to-Play games. This paper explores the problem of rapid retention prediction in this context. Heuristic modeling approaches are introduced as a way of building simple rules for predicting short-term retention. Compared to common classifi…
LineFlow is a framework for training RL agents to control production lines.
Batch normalization (BN) is a technique to normalize activations in intermediate layers of deep neural networks. Its tendency to improve accuracy and speed up training have established BN as a favorite technique in deep learning. Yet, despite its enormous success, there remains little consensus on the exact reason and …
Unified framework proves neural networks' ability to mimic complex tasks.
New method selects features for sequential decision making.
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…
In this paper, we address customer review understanding problems by using supervised machine learning approaches, in order to achieve a fully automatic review aspects categorisation and sentiment analysis. In general, such supervised learning algorithms require domain-specific expert knowledge for generating high quali…
Classifies Bitcoin addresses based on their balance functions.
AGENTICAITA uses AI agents to autonomously trade markets without human intervention.
Understanding the structure of financial markets deals with suitably determining the functional relation between financial variables. In this respect, important variables are the trading activity, defined here as the number of trades , the traded volume , the asset price , the squared volatility , the bid…
MCD offers a complete model understanding for high-stake decisions.
Real artificial intelligence always has been focused on by many machine learning researchers, especially in the area of deep learning. However deep neural network is hard to be understood and explained, and sometimes, even metaphysics. The reason is, we believe that: the network is essentially a perceptual model. There…
New algorithms solve large-scale convex regression problems.
Humans are able to explain their reasoning. On the contrary, deep neural networks are not. This paper attempts to bridge this gap by introducing a new way to design interpretable neural networks for classification, inspired by physiological evidence of the human visual system's inner-workings. This paper proposes a neu…
Hyperplane hashing aims at rapidly searching nearest points to a hyperplane, and has shown practical impact in scaling up active learning with SVMs. Unfortunately, the existing randomized methods need long hash codes to achieve reasonable search accuracy and thus suffer from reduced search speed and large memory overhe…