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.
A new method reduces both input and output dimensions for better goal-oriented analysis.
A new method for experimental design focuses on predicting downstream quantities of interest.
Dialogue research tends to distinguish between chit-chat and goal-oriented tasks. While the former is arguably more naturalistic and has a wider use of language, the latter has clearer metrics and a straightforward learning signal. Humans effortlessly combine the two, for example engaging in chit-chat with the goal of …
GO-CBED optimizes experiments for specific causal queries, improving efficiency.
A new GP interpolation method for better predictive distributions in ranges of interest.
GOIMDA selects inputs to maximize expected influence on a goal functional, reducing data acquisition needs.
The study optimizes sampling in complex systems with probabilistic response distributions.
Learning goal-oriented dialogues by means of deep reinforcement learning has recently become a popular research topic. However, commonly used policy-based dialogue agents often end up focusing on simple utterances and suboptimal policies. To mitigate this problem, we propose a class of novel temperature-based extension…
Developing a dialogue agent that is capable of making autonomous decisions and communicating by natural language is one of the long-term goals of machine learning research. Traditional approaches either rely on hand-crafting a small state-action set for applying reinforcement learning that is not scalable or constructi…
Deep learning improves conversational recommender systems.
Dialogue State Tracking (DST) is a core component of virtual assistants such as Alexa or Siri. To accomplish various tasks, these assistants need to support an increasing number of services and APIs. The Schema-Guided State Tracking track of the 8th Dialogue System Technology Challenge highlighted the DST problem for u…
ClovaCall introduces a new Korean call speech corpus for contact centers.
Attention-based encoder-decoder neural network models have recently shown promising results in goal-oriented dialogue systems. However, these models struggle to reason over and incorporate state-full knowledge while preserving their end-to-end text generation functionality. Since such models can greatly benefit from us…
DGC clusters data with side-information for better prediction.
Learning to solve complex goal-oriented tasks with sparse terminal-only rewards often requires an enormous number of samples. In such cases, using a set of expert trajectories could help to learn faster. However, Imitation Learning (IL) via supervised pre-training with these trajectories may not perform as well and gen…
FastSGT improves accuracy in BERT-based DST for SGD datasets.
Method analyzes hyperparameters using HSIC for better neural network performance.
GO-OED maximizes predictive information gain on nonlinear QoIs.
This paper calibrates Gaussian process predictive distributions for Bayesian optimization to improve sampling decisions.
Unified perspective unites Bayesian optimization and active learning for efficient goal-oriented optimization.
Exploration is a difficult challenge in reinforcement learning and even recent state-of-the art curiosity-based methods rely on the simple epsilon-greedy strategy to generate novelty. We argue that pure random walks do not succeed to properly expand the exploration area in most environments and propose to replace singl…
Solving goal-oriented tasks is an important but challenging problem in reinforcement learning (RL). For such tasks, the rewards are often sparse, making it difficult to learn a policy effectively. To tackle this difficulty, we propose a new approach called Policy Continuation with Hindsight Inverse Dynamics (PCHID). Th…
Teaching machines to accomplish tasks by conversing naturally with humans is challenging. Currently, developing task-oriented dialogue systems requires creating multiple components and typically this involves either a large amount of handcrafting, or acquiring costly labelled datasets to solve a statistical learning pr…
Unmanned Aerial Vehicles (UAVs), autonomously-guided aircraft, are widely used for tasks involving surveillance and reconnaissance. A version of the pursuit-evasion problems centered around UAVs and its variants has been extensively studied in recent years due to numerous breakthroughs in AI. We present an approach to …
The ability to compose learned skills to solve new tasks is an important property of lifelong-learning agents. In this work, we formalise the logical composition of tasks as a Boolean algebra. This allows us to formulate new tasks in terms of the negation, disjunction and conjunction of a set of base tasks. We then sho…
Unified LLM-agent with RL improves financial trading performance.
vsOED optimizes experiment design with reinforcement learning for Bayesian models.
Active learning (AL) concerns itself with learning a model from as few labelled data as possible through actively and iteratively querying an oracle with selected unlabelled samples. In this paper, we focus on analyzing a popular type of AL in which the utility of a sample is measured by a specified goal achieved by th…
Goal-oriented reinforcement learning has recently been a practical framework for robotic manipulation tasks, in which an agent is required to reach a certain goal defined by a function on the state space. However, the sparsity of such reward definition makes traditional reinforcement learning algorithms very inefficien…
Paper tackles offline SSP with value iteration for policy evaluation and learning.
This paper develops a framework for efficient decision-making under time pressure.
Deep reinforcement learning (RL) has been successfully applied to a variety of game-like environments. However, the application of deep RL to visual navigation with realistic environments is a challenging task. We propose a novel learning architecture capable of navigating an agent, e.g. a mobile robot, to a target giv…
As Computer Vision moves from a passive analysis of pixels to active analysis of semantics, the breadth of information algorithms need to reason over has expanded significantly. One of the key challenges in this vein is the ability to identify the information required to make a decision, and select an action that will …
Survey examines agentic AI in finance, highlighting its autonomy and challenges.
Oja's rule improves neural network training without engineered tricks.
CRPS improves GP-based sequential design for chemical space.
Emotions are intimately tied to motivation and the adaptation of behavior, and many animal species show evidence of emotions in their behavior. Therefore, emotions must be related to powerful mechanisms that aid survival, and, emotions must be evolutionary continuous phenomena. How and why did emotions evolve in nature…
In this paper, we consider the problem of building learning agents that can efficiently learn to navigate in constrained environments. The main goal is to design agents that can efficiently learn to understand and generalize to different environments using high-dimensional inputs (a 2D map), while following feasible pa…
Deep learning has improved performance on many natural language processing (NLP) tasks individually. However, general NLP models cannot emerge within a paradigm that focuses on the particularities of a single metric, dataset, and task. We introduce the Natural Language Decathlon (decaNLP), a challenge that spans ten ta…
Many popular reinforcement learning problems (e.g., navigation in a maze, some Atari games, mountain car) are instances of the episodic setting under its stochastic shortest path (SSP) formulation, where an agent has to achieve a goal state while minimizing the cumulative cost. Despite the popularity of this setting, t…
Proposes a real-time anomaly detection system using IRL.
We speed up Gaussian process cross-validation calculations and improve model diagnostics.
Inverse problems are pervasive mathematical methods in inferring knowledge from observational and experimental data by leveraging simulations and models. Unlike direct inference methods, inverse problem approaches typically require many forward model solves usually governed by Partial Differential Equations (PDEs). Thi…
The ability to look multiple times through a series of pose-adjusted glimpses is fundamental to human vision. This critical faculty allows us to understand highly complex visual scenes. Short term memory plays an integral role in aggregating the information obtained from these glimpses and informing our interpretation …
Neuroprosthetic brain-computer interfaces function via an algorithm which decodes neural activity of the user into movements of an end effector, such as a cursor or robotic arm. In practice, the decoder is often learned by updating its parameters while the user performs a task. When the user's intention is not directly…
We present an active learning architecture that allows a robot to actively learn which data collection strategy is most efficient for acquiring motor skills to achieve multiple outcomes, and generalise over its experience to achieve new outcomes. The robot explores its environment both via interactive learning and goal…
Question-answering systems and voice assistants are becoming major part of client service departments of many organizations, helping them to reduce the labor costs of staff. In many such systems, there is always natural language understanding module that solves intent classification task. This task is complicated becau…