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.
Proposes ContSup to boost local learning by supplying context between isolated modules.
In this work, we introduce the Global Planar Convolution module as a building-block for fully-convolutional networks that aggregates global information and, therefore, enhances the context perception capabilities of segmentation networks in the context of brain tumor segmentation. We implement two baseline architecture…
New approach learns causally disentangled latent structures in generative models.
An interesting theme in complex differential geometry is to find a correspondence between algebraic objects and differential geometric objects. One of the most attractive is the non-abelian Hodge theory of Simpson. In this paper, pursuing an analogue of the non-abelian Hodge theory in the context of -difference modu…
NFM improves deep learning by selectively processing hidden states.
We introduce a weak concept of Morita equivalence, in the birational context, for Poisson modules on complex normal Poisson projective varieties. We show that Poisson modules, on projective varieties with mild singularities, are either rationally Morita equivalent to a flat partial holomorphic sheaf, or a sheaf with a …
Proves effective Chen ranks conjecture for Koszul modules.
Mamba struggles with long context lengths, but spectrum scaling improves performance.
Scaling model capacity has been vital in the success of deep learning. For a typical network, necessary compute resources and training time grow dramatically with model size. Conditional computation is a promising way to increase the number of parameters with a relatively small increase in resources. We propose a train…
Many prediction problems, such as those that arise in the context of robotics, have a simplifying underlying structure that, if known, could accelerate learning. In this paper, we present a strategy for learning a set of neural network modules that can be combined in different ways. We train different modular structure…
The Serre-Swan theorem in differential geometry establishes an equivalence between the category of smooth vector bundles over a smooth compact manifold and the category of finitely generated projective modules over the unital ring of smooth functions. This theorem is here generalized to manifolds of bounded geometry. I…
Stability of catenoid in hyperbolic space proven without symmetry assumptions.
In this paper we apply the theory of finitely generated FI-modules developed by Church, Ellenberg and Farb to certain sequences of rational cohomology groups. Our main examples are the cohomology of the moduli space of n-pointed curves, the cohomology of the pure mapping class group of surfaces and some manifolds of hi…
Study the algebraic action of torus on knot complement's skein module.
Details of quantum knot invariant calculations using a specific SU(3)_q-module are given which distinguish the Conway and Kinoshita-Teresaka pair of mutant knots. Features of Kuperberg's skein-theoretic techniques for SU(3)_q invariants in the context of mutant knots are also discussed.
Unified invariant of knots derived from Verma modules.
Develops graphical calculus for monoidal categories with twisted pivotal structures.
The category of finite dimensional module over the quantum superalgebra U_q(sl(2|1)) is not semi-simple and the quantum dimension of a generic U_q(sl(2|1))-module vanishes. This vanishing happens for any value of q (even when q is not a root of unity). These properties make it difficult to create a fusion or modular ca…
Extends Manin triples to Lie bialgebroids over Lie groupoids.
The paper shows the computation of the noncommutative generalization of the A-polynomial of the trefoil knot. The classical A-polynomial was introduced by Cooper, Culler, Gillet, Long and Shalen, and was generalized to the context of Kauffman bracket skein modules by the author in joint work with Frohman and Lofaro. A …
We study a formalization of the grammar induction problem that models sentences as being generated by a compound probabilistic context-free grammar. In contrast to traditional formulations which learn a single stochastic grammar, our grammar's rule probabilities are modulated by a per-sentence continuous latent variabl…
Taxi demand prediction has recently attracted increasing research interest due to its huge potential application in large-scale intelligent transportation systems. However, most of the previous methods only considered the taxi demand prediction in origin regions, but neglected the modeling of the specific situation of …
Improved stock price prediction using attention modules and news sentiment.
CRAUM-Net improves salient object detection with context and uncertainty modeling.
We introduce the notion of a {\vartheta}-summable Fredholm module over a locally convex dg algebra Ω and construct its Chern character as a cocycle on the entire cyclic complex of Ω, extending the construction of Jaffe, Lesniewski and Osterwalder to a differential graded setting. Using this Chern character, we prove an…
This is the second in a series of papers intended to set up a framework to study categories of modules in the context of non-commutative geometries. In \cite{mem} we introduced the basic DG category $\Pc_{\A^\bullet}$, the perfect category of $\A^\bullet$, which corresponded to the category of coherent sheaves on a com…
Shared workspace improves neural module coordination in deep learning.
Paper proposes linear transformers for efficient in-context learning without context length limitations.
Recent dialogue approaches operate by reading each word in a conversation history, and aggregating accrued dialogue information into a single state. This fixed-size vector is not expandable and must maintain a consistent format over time. Other recent approaches exploit an attention mechanism to extract useful informat…
Paper proposes a method to control robots of different shapes efficiently.
We introduce a technique for proving quantitative representation stability theorems for sequences of representations of certain finite linear groups over a field of characteristic zero. In particular, we prove a vanishing result for higher syzygies of VIC- and SI-modules, which can be thought of as a weaker version of …
Animals (especially humans) have an amazing ability to learn new tasks quickly, and switch between them flexibly. How brains support this ability is largely unknown, both neuroscientifically and algorithmically. One reasonable supposition is that modules drawing on an underlying general-purpose sensory representation a…
We give a foundational account on topological racks and quandles. Specifically, we define the notions of ideals, kernels, units, and inner automorphism group in the context of topological racks. Further, we investigate topological rack modules and principal rack bundles. Central extensions of topological racks are then…
Improved sample-efficient learning for non-coherent digital jamming.
The paper studies combinatorics of injective words in the context of Temperley-Lieb algebras.
ForecastGAN improves multi-horizon time series forecasting by integrating numerical and categorical features.
Enhances count process modelling with Markov-modulated non-homogeneous Poisson process.
A commonly cited inefficiency of neural network training by back-propagation is the update locking problem: each layer must wait for the signal to propagate through the full network before updating. Several alternatives that can alleviate this issue have been proposed. In this context, we consider a simpler, but more e…
Paper investigates Lipschitz constants of self-attention modules in neural networks.
BerlinUCB learns from episodic rewards in nonstationary contexts.
Smart devices of everyday use (such as smartphones and wearables) are increasingly integrated with sensors that provide immense amounts of information about a person's daily life such as behavior and context. The automatic and unobtrusive sensing of behavioral context can help develop solutions for assisted living, fit…
We propose a novel visual context-aware filter generation module which incorporates contextual information present in images into Convolutional Neural Networks (CNNs). In contrast to traditional CNNs, we do not employ the same set of learned convolution filters for all input image instances. Our proposed input-conditio…
We describe principal 3-bundles with adjusted connections using Lie algebras and groupoids.
MixFT re-partitions data into sub-domains for better TSFM fine-tuning.
Improved financial sentiment analysis using LLMs with retrieval augmentation.
This paper tackles continuous domain adaptation with a new approach.
New analysis shows PE in Transformers increases generalization gap and vulnerability.
In the early 2000's Cochran and Harvey introduced non-commutative Alexander polynomials for 3-manifolds. Their degrees give strong lower bounds on the Thurston norm. In this paper we make the case that the vanishing of a certain Novikov-Sikorav homology module is the correct notion of a monic non-commutative Alexander …