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.
New technique reduces language biases in large language models.
Study reveals AI's spontaneous topic changes in text prediction.
AI systems that explain their decisions can be monitored for harmful intentions.
Have you ever looked at a machine learning classification model and thought, I could have made that? Well, that is what we test in this project, comparing XGBoost trained on human engineered features to training directly on data. The human engineered features do not outperform XGBoost trained di- rectly on the data, bu…
The Machina thought experiments pose to major non-expected utility models challenges that are similar to those posed by the Ellsberg thought experiments to subjective expected utility theory (SEUT). We test human choices in the `Ellsberg three-color example', confirming typical ambiguity aversion patterns, and the `Mac…
LLMs struggle with financial reasoning but can outperform the market with human oversight.
State of the art deep reinforcement learning algorithms take many millions of interactions to attain human-level performance. Humans, on the other hand, can very quickly exploit highly rewarding nuances of an environment upon first discovery. In the brain, such rapid learning is thought to depend on the hippocampus and…
Injecting human knowledge is an effective way to accelerate reinforcement learning (RL). However, these methods are underexplored. This paper presents our discovery that an abstract forward model (thought-game (TG)) combined with transfer learning (TL) is an effective way. We take StarCraft II as our study environment.…
Text-based representations of chemicals and proteins can be thought of as unstructured languages codified by humans to describe domain-specific knowledge. Advances in natural language processing (NLP) methodologies in the processing of spoken languages accelerated the application of NLP to elucidate hidden knowledge in…
The Gestalt laws of perceptual organization, which describe how visual elements in an image are grouped and interpreted, have traditionally been thought of as innate despite their ecological validity. We use deep-learning methods to investigate whether natural scene statistics might be sufficient to derive the Gestalt …
Machine learning uses crowdworkers; determining their status as human subjects is tricky.
Convolutional Neural Networks (CNNs) are commonly thought to recognise objects by learning increasingly complex representations of object shapes. Some recent studies suggest a more important role of image textures. We here put these conflicting hypotheses to a quantitative test by evaluating CNNs and human observers on…
Posterior sampling for reinforcement learning (PSRL) is an effective method for balancing exploration and exploitation in reinforcement learning. Randomised value functions (RVF) can be viewed as a promising approach to scaling PSRL. However, we show that most contemporary algorithms combining RVF with neural network f…
A method for learning with autoregressive chain-of-thoughts.
The Allais and Ellsberg paradoxes show that the expected utility hypothesis and Savage's Sure-Thing Principle are violated in real life decisions. The popular explanation in terms of 'ambiguity aversion' is not completely accepted. On the other hand, we have recently introduced a notion of 'contextual risk' to mathemat…
Can an algorithm create original and compelling fashion designs to serve as an inspirational assistant? To help answer this question, we design and investigate different image generation models associated with different loss functions to boost creativity in fashion generation. The dimensions of our explorations include…
Machine learning tasks entail the use of complex computational pipelines to reach quantitative and qualitative conclusions. If some of the activities in a pipeline produce erroneous or uninformative outputs, the pipeline may fail or produce incorrect results. Inferring the root cause of failures and unexpected behavior…
Recent work in reinforcement learning demonstrated that learning solely through self-play is not only possible, but could also result in novel strategies that humans never would have thought of. However, optimization methods cast as a game between two players require careful tuning to prevent suboptimal results. Hence,…
The visual systems of many mammals, including humans, is able to integrate the geometric information of visual stimuli and to perform cognitive tasks already at the first stages of the cortical processing. This is thought to be the result of a combination of mechanisms, which include feature extraction at single cell l…
LTMs use latent vectors for efficient autoregressive generation.
This paper introduces a machine for sampling approximate model-X knockoffs for arbitrary and unspecified data distributions using deep generative models. The main idea is to iteratively refine a knockoff sampling mechanism until a criterion measuring the validity of the produced knockoffs is optimized; this criterion i…
Protein Thoughts interprets protein interactions with clear reasoning, improving prediction accuracy.
A new method for math reasoning that allows for iterative correction.
Supervised machine learning models boast remarkable predictive capabilities. But can you trust your model? Will it work in deployment? What else can it tell you about the world? We want models to be not only good, but interpretable. And yet the task of interpretation appears underspecified. Papers provide diverse and s…
SelfReflect measures LLM uncertainty by summarizing belief distribution.
Optimal sample complexity for autoregressive chain-of-thought learning proven.
Transformers learn chain-of-thought reasoning for longer problems, proving length generalization.
Prefix consistency improves model reliability by weighting answers based on their reproducibility.
FinRobot AI agent for equity research provides comprehensive insights.
New system resists meme coin copy trading bots.
New framework for task-independent legged locomotion.
This paper improves learning complex functions with CoT supervision, reducing sample complexity.
Theoretical work shows integrating coherent reasoning improves LLM performance and error correction.
This work analyzes CoT prompting methods from a statistical estimation perspective.
A (complete) matching of the cells of a triangulated manifold can be thought as a combinatorial or discrete version of a nonsingular vector field. We give several methods for constructing such matchings.
Summarizes financial news for better investment decisions.
EORM boosts LLM accuracy with a lightweight, energy-based verifier.
Transformers solve parity problems efficiently with step-by-step reasoning.
Study reveals how depth of reasoning affects generalization in models.
CoT-UQ improves LLM uncertainty quantification by integrating reasoning steps.
We prove a compactness result for minimal hypersurfaces with bounded index and volume, which can be thought of as an extension of the compactness theorem of Choi-Schoen (Invent. Math. 1985) to higher dimensions.
Fractured Sampling improves LLM reasoning efficiency by truncating CoT trajectories.
The paper studies how search and distillation improve reasoning in large language models.
The paper explores how LLMs with CoT improve performance on complex tasks.
Curriculum learning improves model training efficiency and performance.
CoT enhances transformer accuracy on serial tasks by enabling serial computation.
A conformal procedure improves CoT reasoning by aggregating reasoning paths and calibrating abstention rules.
Deep learning has recently seen rapid development and received significant attention due to its state-of-the-art performance on previously-thought hard problems. However, because of the internal complexity and nonlinear structure of deep neural networks, the underlying decision making processes for why these models are…