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.
End-to-end KBQA system learns from multiple reasoning paths without labeled paths.
Transformers learn multi-step reasoning through gradient descent.
Improved RL for knowledge graph reasoning with entity types.
A conformal procedure improves CoT reasoning by aggregating reasoning paths and calibrating abstention rules.
Neural-symbolic model improves link prediction in knowledge graphs.
Without relevant human priors, neural networks may learn uninterpretable features. We propose Dynamics of Attention for Focus Transition (DAFT) as a human prior for machine reasoning. DAFT is a novel method that regularizes attention-based reasoning by modelling it as a continuous dynamical system using neural ordinary…
Inferring new facts from existing knowledge graphs (KG) with explainable reasoning processes is a significant problem and has received much attention recently. However, few studies have focused on relation types unseen in the original KG, given only one or a few instances for training. To bridge this gap, we propose Co…
Auto-CEI improves LLM reasoning by balancing assertiveness and conservativeness.
Neural networks have succeeded in many reasoning tasks. Empirically, these tasks require specialized network structures, e.g., Graph Neural Networks (GNNs) perform well on many such tasks, but less structured networks fail. Theoretically, there is limited understanding of why and when a network structure generalizes be…
Theoretical work shows integrating coherent reasoning improves LLM performance and error correction.
Tractograms are mathematical representations of the main paths of axons within the white matter of the brain, from diffusion MRI data. Such representations are in the form of polylines, called streamlines, and one streamline approximates the common path of tens of thousands of axons. The analysis of tractograms is a ta…
Proposes CLRS-Text, a new benchmark for evaluating LM reasoning capabilities.
ManifoldMind uses adaptive-curvature probabilistic spheres for trustworthy recommendations in semantic hierarchies.
NSR enables neural networks to reason with continuous numbers and extrapolate.
ERM uses energy-based selection to improve recursive reasoning.
Reasoning models generate differently based on problem difficulty, not just length.
Knowledge base (KB) completion adds new facts to a KB by making inferences from existing facts, for example by inferring with high likelihood nationality(X,Y) from bornIn(X,Y). Most previous methods infer simple one-hop relational synonyms like this, or use as evidence a multi-hop relational path treated as an atomic f…
EORM boosts LLM accuracy with a lightweight, energy-based verifier.
We establish causal semantics for SDEs and develop methods to reason about them.
We propose the Neural Logic Machine (NLM), a neural-symbolic architecture for both inductive learning and logic reasoning. NLMs exploit the power of both neural networks---as function approximators, and logic programming---as a symbolic processor for objects with properties, relations, logic connectives, and quantifier…
G1 uses RL to enhance LLMs' graph reasoning, improving performance on diverse tasks.
Improved Markov models learn from their mistakes and adapt to problem complexity.
Language grounded image understanding tasks have often been proposed as a method for evaluating progress in artificial intelligence. Ideally, these tasks should test a plethora of capabilities that integrate computer vision, reasoning, and natural language understanding. However, rather than behaving as visual Turing t…
FinReflectKG benchmarks financial QA by linking relevant context from a financial KG, improving model performance and efficiency.
Proposes a copula-based method to interpret neural networks.
Fuelled by increasing computer power and algorithmic advances, machine learning techniques have become powerful tools for finding patterns in data. Since quantum systems produce counter-intuitive patterns believed not to be efficiently produced by classical systems, it is reasonable to postulate that quantum computers …
New algorithm reduces regret in stochastic shortest path problems.
Improves many-shot learning by optimizing and generating influential examples.
The majority of contemporary object-tracking approaches do not model interactions between objects. This contrasts with the fact that objects' paths are not independent: a cyclist might abruptly deviate from a previously planned trajectory in order to avoid colliding with a car. Building upon HART, a neural class-agnost…
Machine learning models have become more and more complex in order to better approximate complex functions. Although fruitful in many domains, the added complexity has come at the cost of model interpretability. The once popular k-nearest neighbors (kNN) approach, which finds and uses the most similar data for reasonin…
We consider as given a discrete time financial market with a risky asset and options written on that asset and determine both the sub- and super-hedging prices of an American option in the model independent framework of ArXiv:1305.6008. We obtain the duality of results for the sub- and super-hedging prices. For the sub…
Careful tuning of a regularization parameter is indispensable in many machine learning tasks because it has a significant impact on generalization performances. Nevertheless, current practice of regularization parameter tuning is more of an art than a science, e.g., it is hard to tell how many grid-points would be need…
We introduce the value iteration network (VIN): a fully differentiable neural network with a `planning module' embedded within. VINs can learn to plan, and are suitable for predicting outcomes that involve planning-based reasoning, such as policies for reinforcement learning. Key to our approach is a novel differentiab…
New model enables AI to learn autonomously.
SAM improves deep learning by relaxing Bayes objective.
String geometry theory uniquely determines classical action with T-symmetry.
We propose a novel method for fact-checking on knowledge graphs based on debate dynamics. The underlying idea is to frame the task of triple classification as a debate game between two reinforcement learning agents which extract arguments -- paths in the knowledge graph -- with the goal to justify the fact being true (…
Survey examines distillation methods for large language models.
INFUSER improves reasoning by co-evolving a generator and solver with adaptive curriculum.
INFUSER improves reasoning by self-evolving with a generator and solver that co-learn from unstructured documents.
A novel method for visual question answering using scene graphs and reinforcement learning.
We propose a novel method for automatic reasoning on knowledge graphs based on debate dynamics. The main idea is to frame the task of triple classification as a debate game between two reinforcement learning agents which extract arguments -- paths in the knowledge graph -- with the goal to promote the fact being true (…
SPO optimizes LLMs by eliminating group-based baselines and variance issues.
This paper develops a novel methodology for using symbolic knowledge in deep learning. From first principles, we derive a semantic loss function that bridges between neural output vectors and logical constraints. This loss function captures how close the neural network is to satisfying the constraints on its output. An…
Automates hair color digitization using imaging and deep learning.
We consider a fractional version of the Heston volatility model which is inspired by [16]. Within this model we treat portfolio optimization problems for power utility functions. Using a suitable representation of the fractional part, followed by a reasonable approximation we show that it is possible to cast the proble…
SeqRF straightens generative model flows to speed up sampling.
We provide a lean, non-technical exposition on the pricing of path-dependent and European-style derivatives in the Cox-Ross-Rubinstein (CRR) pricing model. The main tool used in the paper for cleaning up the reasoning is applying static hedging arguments. This can be accomplished by taking various routes through some a…