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.
DREAM learns optimal strategies in imperfect games without needing a simulator.
DREAM model improves computational efficiency for non-linear effects in relational event models.
Learning to control robots directly based on images is a primary challenge in robotics. However, many existing reinforcement learning approaches require iteratively obtaining millions of robot samples to learn a policy, which can take significant time. In this paper, we focus on learning a realistic world model capturi…
LiDER refreshes past experiences in RL by dreaming about them.
Model compression is eminently suited for deploying deep learning on IoT-devices. However, existing model compression techniques rely on access to the original or some alternate dataset. In this paper, we address the model compression problem when no real data is available, e.g., when data is private. To this end, we p…
Reduces symplectic Hamiltonian systems to contact systems, realizing Poincaré's dream.
ESCHER avoids importance sampling to estimate regret in large games.
Study shows non-polyhedral structure in moduli spaces for n≥8.
RL research overhypes potential but lacks deployable solutions.
New meta-RL method avoids exploration-exploitation trade-off.
Machine learning models learn what we teach them to learn. Machine learning is at the heart of recommender systems. If a machine learning model is trained on biased data, the resulting recommender system may reflect the biases in its recommendations. Biases arise at different stages in a recommender system, from existi…
In this paper, we introduce playing games on shadows of knots. We demonstrate two novel games, namely, To Knot or Not to Knot and Much Ado about Knotting. We also discuss winning strategies for these games on certain families of knot shadows. Finally, we suggest variations of these games for further study.
We show that any bounded zero-angular momentum solution for the Newtonian three-body problem must suffer infinitely many eclipses, or collinearities, provided that it does not suffer a triple collision. Motivation for the result comes from the dream of building a symbolic dynamics for the three-body problem, one whose …
We consider a quasi-metric topological structure for the construction of a new reinforcement learning model in the framework of financial markets. It is based on a Lipschitz type extension of reward functions defined in metric spaces. Specifically, the McShane and Whitney extensions are considered for a reward function…
Reductive quotients preserve klt singularities in algebraic geometry.
New Dreamer model tackles object vanishing in robot learning.
A neural network learns from examples and optimizes by dreaming.
Develops a method to estimate optimal policy value in online learning.
Dimofte, Gaiotto and Gukov introduced a powerful invariant, the 3D-index, associated to a suitable ideal triangulation of a 3-manifold with torus boundary components. The 3D-index is a collection of formal power series in with integer coefficients. Our goal is to explain how the 3D-index is a generating serie…
We explore building generative neural network models of popular reinforcement learning environments. Our world model can be trained quickly in an unsupervised manner to learn a compressed spatial and temporal representation of the environment. By using features extracted from the world model as inputs to an agent, we c…
We consider projective rational strong Calabi dream surfaces: projective smooth rational surfaces which admit a constant scalar curvature Kähler metric for every Kähler class. We show that there are only two such rational surfaces, namely the projective plane and the quadric surface. In particular, we show that all rat…
We propose generative neural network methods to generate DNA sequences and tune them to have desired properties. We present three approaches: creating synthetic DNA sequences using a generative adversarial network; a DNA-based variant of the activation maximization ("deep dream") design method; and a joint procedure wh…
We posit that hippocampal place cells encode information about future locations under a transition distribution observed as an agent explores a given (physical or conceptual) space. The encoding of information about the current location, usually associated with place cells, then emerges as a necessary step to achieve t…
The common view that our creativity is what makes us uniquely human suggests that incorporating research on human creativity into generative deep learning techniques might be a fruitful avenue for making their outputs more compelling and human-like. Using an original synthesis of Deep Dream-based convolutional neural n…
Survey on quantum computing and neural networks.
We discuss a recurrent geometrical method, due to Élie Cartan and von Weber ([1],[11]) enabling us to determine, step by step, the maximal integral manifolds of a not necessarily integrable nor regular Pfaffian system. The dimensions of such integral manifolds can, of course, vary from point to point but more so can va…
LLMs can be tricked into recalling facts based on context clues.
New sampler tackles complex discrete energy landscapes efficiently.
With the horrific Jamal Khashoggi killing, Mohammed Bin Salman's image in the international community has been damaged. This study seeks to test whether Khashoggi murder discourage businesses from investing in Saudi Arabia. We use an event-study methodology and asset pricing model to assess, at sectoral level, the dyna…
Expands experimental design for causal discovery from limited data.
Paper uses diffusion models to design electric aircraft quickly.
Motivation: Modelling methods that find structure in data are necessary with the current large volumes of genomic data, and there have been various efforts to find subsets of genes exhibiting consistent patterns over subsets of treatments. These biclustering techniques have focused on one data source, often gene expres…
Develops a nonparametric graphical model for conditional independence.
We introduce DeepInversion, a new method for synthesizing images from the image distribution used to train a deep neural network. We 'invert' a trained network (teacher) to synthesize class-conditional input images starting from random noise, without using any additional information about the training dataset. Keeping …
Automatic classification of trees using remotely sensed data has been a dream of many scientists and land use managers. Recently, Unmanned aerial vehicles (UAV) has been expected to be an easy-to-use, cost-effective tool for remote sensing of forests, and deep learning has attracted attention for its ability concerning…
In this paper we provide an explicit formula for the optimal lower bound of Donaldson's J-functional, in the sense of finding explicitly the optimal constant in the definition of coercivity, which always exists and takes negative values in general. This constant is positive precisely if the J-equation admits a solution…
Advances in neural network based classifiers have transformed automatic feature learning from a pipe dream of stronger AI to a routine and expected property of practical systems. Since the emergence of AlexNet every winning submission of the ImageNet challenge has employed end-to-end representation learning, and due to…
The vast majority of current machine learning algorithms are designed to predict single responses or a vector of responses, yet many types of response are more naturally organized as matrices or higher-order tensor objects where characteristics are shared across modes. We present a new machine learning algorithm BaTFLE…
LLMs can simulate human investment attitudes based on personality traits.
While the costs of human violence have attracted a great deal of attention from the research community, the effects of the network-on-network (NoN) violence popularised by Generative Adversarial Networks have yet to be addressed. In this work, we quantify the financial, social, spiritual, cultural, grammatical and derm…
A new inference method using regression and batched discrepancies.
Wilson-loop averages in Chern-Simons theory (HOMFLY polynomials) can be evaluated in different ways -- the most difficult, but most interesting of them is the hypercube calculus, the only one applicable to virtual knots and used also for categorification (higher-dimensional extension) of the theory. We continue the stu…
Wavelet scattering predicts material properties beyond training data.
New method identifies precursors of financial crises in market correlation structures.
Overcoming the visual barrier and developing "see-through vision" has been one of mankind's long-standing dreams. Unlike visible light, Radio Frequency (RF) signals penetrate opaque obstructions and reflect highly off humans. This paper establishes a deep-learning model that can be trained to reconstruct continuous vid…
Study reveals widespread manipulation of meme coins, leading to significant economic losses.
Bayesian approach infers signaling pathways from data.
The paper reveals the hidden costs of digitizing commodity money and proposes a new stable-coin system.