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.
Paper proposes DAC-ML, a cognitive architecture that learns quickly from few episodes.
We propose a fully distributed actor-critic algorithm approximated by deep neural networks, named \textit{Diff-DAC}, with application to single-task and to average multitask reinforcement learning (MRL). Each agent has access to data from its local task only, but it aims to learn a policy that performs well on average …
We propose a deep amortized clustering (DAC), a neural architecture which learns to cluster datasets efficiently using a few forward passes. DAC implicitly learns what makes a cluster, how to group data points into clusters, and how to count the number of clusters in datasets. DAC is meta-learned using labelled dataset…
Tree ensembles, such as random forests and AdaBoost, are ubiquitous machine learning models known for achieving strong predictive performance across a wide variety of domains. However, this strong performance comes at the cost of interpretability (i.e. users are unable to understand the relationships a trained random f…
Graph neural network optimizes energy-efficient precoding for massive MIMO systems.
What is the role of real-time control and learning in the formation of social conventions? To answer this question, we propose a computational model that matches human behavioral data in a social decision-making game that was analyzed both in discrete-time and continuous-time setups. Furthermore, unlike previous approa…
DeepAveragers solves offline RL by solving derived MDPs from static data.
We reformulate the option framework as two parallel augmented MDPs. Under this novel formulation, all policy optimization algorithms can be used off the shelf to learn intra-option policies, option termination conditions, and a master policy over options. We apply an actor-critic algorithm on each augmented MDP, yieldi…
DAC enhances exploration in reinforcement learning with entropy regularization.
State representation learning (SRL) in partially observable Markov decision processes has been studied to learn abstract features of data useful for robot control tasks. For SRL, acquiring domain-agnostic states is essential for achieving efficient imitation learning. Without these states, imitation learning is hampere…
Supervised learning algorithms are nowadays successfully scaling up to datasets that are very large in volume, leveraging the potential of in-memory cluster-computing Big Data frameworks. Still, massive datasets with a number of large-domain categorical features are a difficult challenge for any classifier. Most off-th…
Fundamental to robotics is the debate between model-based and model-free learning: should the robot build an explicit model of the world, or learn a policy directly? In the context of HRI, part of the world to be modeled is the human. One option is for the robot to treat the human as a black box and learn a policy for …
We introduce a novel method to combat label noise when training deep neural networks for classification. We propose a loss function that permits abstention during training thereby allowing the DNN to abstain on confusing samples while continuing to learn and improve classification performance on the non-abstained sampl…
We propose a new algorithm for training neural networks with binary activations and multi-level weights, which enables efficient processing-in-memory circuits with embedded nonvolatile memories (eNVM). Binary activations obviate costly DACs and ADCs. Multi-level weights leverage multi-level eNVM cells. Compared to exis…
TT-DAC-PS: A deterministic actor-critic approach for optimal trade execution
Minding's most celebrated result is his namesake theorem of 1839 which established that all surfaces having the same constant curvature must be locally isometric. Today, Minding's theorem is a staple in differential geometry textbooks. But, to the best of our knowledge, all published proofs of it, inclusive of Minding'…
We prove Minding's Theorem for -immersions with constant negative Gauss curvature. As a Corollary we also prove Minding's Theorem for -immersions in the sense of \cite{DS}.
In this paper, we firstly introduce a method to efficiently implement large-scale high-dimensional convolution with realistic memristor-based circuit components. An experiment verified simulator is adapted for accurate prediction of analog crossbar behavior. An improved conversion algorithm is developed to convert conv…
Most of the prior work on multi-agent reinforcement learning (MARL) achieves optimal collaboration by directly controlling the agents to maximize a common reward. In this paper, we aim to address this from a different angle. In particular, we consider scenarios where there are self-interested agents (i.e., worker agent…
Image clustering is an important but challenging task in machine learning. As in most image processing areas, the latest improvements came from models based on the deep learning approach. However, classical deep learning methods have problems to deal with spatial image transformations like scale and rotation. In this p…
The Hamilton-Jacobi problem is revisited bearing in mind the consequences arising from a possible bi-Hamiltonian structure. The problem is formulated on the tangent bundle for Lagrangian systems in order to avoid the bias of the existence of a natural symplectic structure on the cotangent bundle. First it is developed …
A major challenge in cognitive science and AI has been to understand how autonomous agents might acquire and predict behavioral and mental states of other agents in the course of complex social interactions. How does such an agent model the goals, beliefs, and actions of other agents it interacts with? What are the com…
The Audio/Visual Emotion Challenge and Workshop (AVEC 2019) "State-of-Mind, Detecting Depression with AI, and Cross-cultural Affect Recognition" is the ninth competition event aimed at the comparison of multimedia processing and machine learning methods for automatic audiovisual health and emotion analysis, with all pa…
Theory broadens GFlowNets to handle continuous spaces.
In this paper we explain how Morse theory for the Yang-Mills functional can be used to prove an analogue, for surface groups, of the Atiyah-Segal theorem. Classically, the Atiyah-Segal theorem relates the representation ring R(Γ) of a compact Lie group to the complex K-theory of the classifying space . For infi…
This paper proposes GProp, a deep reinforcement learning algorithm for continuous policies with compatible function approximation. The algorithm is based on two innovations. Firstly, we present a temporal-difference based method for learning the gradient of the value-function. Secondly, we present the deviator-actor-cr…
Automated prediction of valence, one key feature of a person's emotional state, from individuals' personal narratives may provide crucial information for mental healthcare (e.g. early diagnosis of mental diseases, supervision of disease course, etc.). In the Interspeech 2018 ComParE Self-Assessed Affect challenge, the …
The set of factorizations of permutations in to transpositions of some symmetric group is naturally in bijection with the set of graphs of order and size with both edges and vertices labeled. We define a notion of duality (the \emph{mind-body duality}) for factorizations and such labeled gra…
Mind wandering (MW) is a ubiquitous phenomenon which reflects a shift in attention from task-related to task-unrelated thoughts. There is a need for intelligent interfaces that can reorient attention when MW is detected due to its detrimental effects on performance and productivity. In this paper, we propose a deep lea…
We adapt the theory of currents in metric spaces, as developed by the first-mentioned author in collaboration with B. Kirchheim, to currents with coefficients in Z_p. Building on S. Wenger's work in the orientable case, we obtain isoperimetric inequalities mod(p) in Banach spaces and we apply these inequalities to prov…
Industrial recommender systems usually consist of the matching stage and the ranking stage, in order to handle the billion-scale of users and items. The matching stage retrieves candidate items relevant to user interests, while the ranking stage sorts candidate items by user interests. Thus, the most critical ability i…
A crypto coin designed to provide a stabilization instrument backed up by minded like financial investments instruments to maintain the purchase value of savings across time, in order to construct new tools for unstable economies.
In this paper we propose a generalization of deep neural networks called deep function machines (DFMs). DFMs act on vector spaces of arbitrary (possibly infinite) dimension and we show that a family of DFMs are invariant to the dimension of input data; that is, the parameterization of the model does not directly hinge …
In the jet-bundle description of first-order classical field theories there are some elements, such as the lagrangian energy and the construction of the hamiltonian formalism, which require the prior choice of a connection. Bearing these facts in mind, we analyze the situation in the jet-bundle description of time-depe…
This paper deals with optimally-robust parameter estimation in generalized Pareto distributions (GPDs). These arise naturally in many situations where one is interested in the behavior of extreme events as motivated by the Pickands-Balkema-de Haan extreme value theorem (PBHT). The application we have in mind is calcula…
Manifolds without boundary, and manifolds with boundary, are universally known in Differential Geometry, but manifolds with corners (locally modelled on [0,\infty)^k x R^{n-k}) have received comparatively little attention. The basic definitions in the subject are not agreed upon, there are several inequivalent definiti…
Game-theoretic analysis of mining gaps in blockchain systems.
Paper questions RNN and LSTM's long-term memory and introduces a new definition.
The so-called great divergence in the income per capita is described in the Unified Growth Theory as the mind-boggling and unresolved mystery about the growth process. This mystery has now been solved: the great divergence never happened. It was created by the manipulation of data. Economic growth in various regions is…
We give an alternative proof of Madsen-Weiss' generalized Mumford conjecture. Our proof is based on ideas similar to Madsen-Weiss' original proof, but it is more geometrical and less homotopy theoretical in nature. At the heart of the argument is a geometric version of Harer stability, which we formulate as a theorem a…
Control of drawdown, that is, the control of the drops in wealth over time from peaks to subsequent lows, is of great concern from a risk management perspective. With this motivation in mind, the focal point of this paper is to address the drawdown issue in a stock trading context. Although our analysis can be carried …
Using a recently introduced method to quantify the time varying lead-lag dependencies between pairs of economic time series (the thermal optimal path method), we test two fundamental tenets of the theory of fixed income: (i) the stock market variations and the yield changes should be anti-correlated; (ii) the change in…
MIND estimates mutual information from ordinal data without full distributional knowledge.
The present paper considers if the new proposed conformal geometrodynamics (CGD) can extend the Nature features compared with general theory of relativity (GTR). The answer for this question can be connected with unique phenomenon arising from Riemann space transition used in GTR, to Weyl space used in CGD. We have in …
Deep learning has sparked a network of mutual interactions between different disciplines and AI. Naturally, each discipline focuses and interprets the workings of deep learning in different ways. This diversity of perspectives on deep learning, from neuroscience to statistical physics, is a rich source of inspiration t…
We propose a novel active learning framework for activity recognition using wearable sensors. Our work is unique in that it takes physical and cognitive limitations of the oracle into account when selecting sensor data to be annotated by the oracle. Our approach is inspired by human-beings' limited capacity to respond …
This work is done as part of a master's thesis project. The increase in the volume of data has given rise to various issues related to the collection, storage, analysis and exploitation of these data in order to create an added value. In this master, we are interested in the search of frequent closed patterns in the tr…
MINDE estimates Mutual Information using neural diffusion models.