arXiv research

EDRBO optimizes Bayesian optimization with continuous contexts using ensemble models and robust methods.

HiPPO-Prophecy models can learn dynamical systems without fine-tuning.

This paper improves continuous adversarial training for LLMs using in-context learning theory.

We solve the differentiability problem for the evolution map in Milnor's infinite dimensional setting. We first show that the evolution map of each $C^k$-semiregular Lie group $G$ (for $k\in \mathbb{N}\sqcup\{\mathrm{lip},\infty\}$) admits a particular kind of sequentially continuity $-$ called Mackey k-continuity. We …

This work investigates how context should be taken into account when performing continuous authentication of a smartphone user based on touchscreen and accelerometer readings extracted from swipe gestures. The study is conducted on the publicly available HMOG dataset consisting of 100 study subjects performing pre-defi…

New algorithm for context bandits with continuous actions.

Transformers can predict new tokens based on any number of context tokens, approximating continuous mappings with fixed resources.

Bayesian optimization tackles uncertainty in context variables.

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…

MLPs can approximate any function in context, challenging the importance of in-context universality.

This paper gives yet another definition of game-theoretic probability in the context of continuous-time idealized financial markets. Without making any probabilistic assumptions (but assuming positive and continuous price paths), we obtain a simple expression for the equity premium and derive a version of the capital a…

This paper describes recent development and test implementation of a continuous time recurrent neural network that has been configured to predict rates of change in securities. It presents outcomes in the context of popular technical analysis indicators and highlights the potential impact of continuous predictive capab…

We study the stability of several no-arbitrage conditions with respect to absolutely continuous, but not necessarily equivalent, changes of measure. We first consider models based on continuous semimartingales and show that no-arbitrage conditions weaker than NA and NFLVR are always stable. Then, in the context of gene…

Proposes DeepSDRF for continuous treatment recommendation from clinical survival data.

Continuous-time event sequences represent discrete events occurring in continuous time. Such sequences arise frequently in real-life. Usually we expect the sequences to follow some regular pattern over time. However, sometimes these patterns may be interrupted by unexpected absence or occurrences of events. Identificat…

The Lebesgue property (order-continuity) of a monotone convex function on a solid vector space of measurable functions is characterized in terms of (1) the weak inf-compactness of the conjugate function on the order-continuous dual space, (2) the attainment of the supremum in the dual representation by order-continuous…

Method discovers local independence in systems with continuous variables.

A new method for CT-DCEGs simplifies inference for asymmetric processes.

We derive the Chern-Gauss-Bonnet Theorem for manifolds with smooth non-degenerate boundary in the pseudo-Riemannian context from the corresponding result in the Riemannian setting by examining the Euler-Lagrange equations associated to the Pfaffian of a complex "metric" on the tangent space and then applying analytic c…

Continuous time stochastic processes are useful models especially for financial and insurance purposes. The numerical simulation of such models is dependant of the time discrete discretization, of the parametric estimation and of the choice of a random number generator. The aim of this paper is to provide the tools for…

New algorithm achieves consistent learning from context in bandit problems.

Paper explores using LLMs for zero-shot reinforcement learning in continuous spaces.

Researchers prove an equivariant index theorem on Euclidean space.

BFNs use Bayesian inference and neural networks for generative modeling.

Transformers preserve support and can approximate any continuous map.

ContextFlow++ improves generative models by conditioning on mixed-variable contexts.

Word embedding maps words into a low-dimensional continuous embedding space by exploiting the local word collocation patterns in a small context window. On the other hand, topic modeling maps documents onto a low-dimensional topic space, by utilizing the global word collocation patterns in the same document. These two …

In a voice-controlled smart-home, a controller must respond not only to user's requests but also according to the interaction context. This paper describes Arcades, a system which uses deep reinforcement learning to extract context from a graphical representation of home automation system and to update continuously its…

A variety of machine learning models have been proposed to assess the performance of players in professional sports. However, they have only a limited ability to model how player performance depends on the game context. This paper proposes a new approach to capturing game context: we apply Deep Reinforcement Learning (…

Characterizes billiard and quasigeodesic flows in polyhedral convex bodies.

New method uses kernel Stein discrepancy for measure transport without strict continuity constraints.

Context-awareness in smart mobile applications is a growing area of study, because of it's intelligence in the applications. In order to build context-aware intelligent applications, mining contextual behavioral rules of individual smartphone users utilizing their phone log data is the key. However, to mine these rules…

A new approach to continuous-time universal portfolios using pathwise Itô calculus.

We consider models of the population or opinion dynamics which result in the non-linear stochastic differential equations (SDEs) exhibiting the spurious long-range memory. In this context, the correspondence between the description of the birth-death processes as the continuous-time Markov chains and the continuous SDE…

A fundamental challenge in artificial intelligence is to build an agent that generalizes and adapts to unseen environments. A common strategy is to build a decoder that takes the context of the unseen new environment as input and generates a policy accordingly. The current paper studies how to build a decoder for the f…

We show that an infinite dimensional Lie group in Milnor's sense has the strong Trotter property if it is locally $μ$-convex. This is a continuity condition imposed on the Lie group multiplication that generalizes the triangle inequality for locally convex vector spaces, and is equivalent to $C^0$-continuity of the evo…

Consider the one-parameter generalizations of the logarithmic and exponential functions which are obtained from the integration of non-symmetrical hyperboles. These generalizations coincide to the one obtained in the context of non-extensive thermostatistics. We show that these functions are suitable to describe and un…

New Transformers maintain Lipschitz continuity for robustness.

We examine the impact of learning Lipschitz continuous models in the context of model-based reinforcement learning. We provide a novel bound on multi-step prediction error of Lipschitz models where we quantify the error using the Wasserstein metric. We go on to prove an error bound for the value-function estimate arisi…

New online few-shot learning model for context-aware recognition.

New method detects symmetries beyond affine transformations.

With a simple architecture and the ability to learn meaningful word embeddings efficiently from texts containing billions of words, word2vec remains one of the most popular neural language models used today. However, as only a single embedding is learned for every word in the vocabulary, the model fails to optimally re…

Paper tackles continual learning with single-index models, proving regret bounds.

VAEs (Variational AutoEncoders) have proved to be powerful in the context of density modeling and have been used in a variety of contexts for creative purposes. In many settings, the data we model possesses continuous attributes that we would like to take into account at generation time. We propose in this paper GLSR-V…

DG improves policy gradients by weighting actions with a sigmoid of advantage and surprisal.

New framework discovers non-affine continuous symmetries in neural networks.

In contextual continuum-armed bandits, the contexts $x$ and the arms $y$ are both continuous and drawn from high-dimensional spaces. The payoff function to learn $f(x,y)$ does not have a particular parametric form. The literature has shown that for Lipschitz-continuous functions, the optimal regret is $\tilde{O}(T^{\fr…

Study continuity of limit sets in symmetric spaces.