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.
New federated learning protocols improve on knowledge distillation's poor performance.
L2R learns to denoise images without needing noise distribution knowledge.
This paper tackles continuous domain adaptation with a new approach.
Paper analyzes error exponent in agnostic PAC learning.
NSGD-M optimizes machine learning models without hyperparameter tuning, even under relaxed smoothness.
This paper aims to analyze knowledge consistency between pre-trained deep neural networks. We propose a generic definition for knowledge consistency between neural networks at different fuzziness levels. A task-agnostic method is designed to disentangle feature components, which represent the consistent knowledge, from…
Current deep learning based text classification methods are limited by their ability to achieve fast learning and generalization when the data is scarce. We address this problem by integrating a meta-learning procedure that uses the knowledge learned across many tasks as an inductive bias towards better natural languag…
NeAda solves nonconvex minimax optimization by balancing primal and dual variables adaptively.
Framework evaluates the impact of prior knowledge in deep learning models.
New algorithm reduces prediction error in online learning without knowing base measure.
FedZKT enables resource-constrained devices to participate in federated learning with heterogeneous models.
DACL tackles domain-specific contrastive learning by using Mixup noise.
New algorithms for linear bandits avoid norm knowledge, reducing regret.
i-Mix improves contrastive learning across domains without domain-specific augmentations.
Knowledge graph embeddings rank among the most successful methods for link prediction in knowledge graphs, i.e., the task of completing an incomplete collection of relational facts. A downside of these models is their strong sensitivity to model hyperparameters, in particular regularizers, which have to be extensively …
Develops a transparent surrogate model for complex data.
In most cases deep learning architectures are trained disregarding the amount of operations and energy consumption. However, some applications, like embedded systems, can be resource-constrained during inference. A popular approach to reduce the size of a deep learning architecture consists in distilling knowledge from…
We consider Model-Agnostic Meta-Learning (MAML) methods for Reinforcement Learning (RL) problems, where the goal is to find a policy using data from several tasks represented by Markov Decision Processes (MDPs) that can be updated by one step of stochastic policy gradient for the realized MDP. In particular, using stoc…
Proposes a method to use causal graph knowledge for better predictive modeling.
Knowledge Distillation (KD) is a model-agnostic technique to improve model quality while having a fixed capacity budget. It is a commonly used technique for model compression, where a larger capacity teacher model with better quality is used to train a more compact student model with better inference efficiency. Throug…
Task-agnostic data valuation without validation requirements.
New method prevents forgetting in learning new tasks.
For many machine learning algorithms, two main assumptions are required to guarantee performance. One is that the test data are drawn from the same distribution as the training data, and the other is that the model is correctly specified. In real applications, however, we often have little prior knowledge on the test d…
The broad set of deep generative models (DGMs) has achieved remarkable advances. However, it is often difficult to incorporate rich structured domain knowledge with the end-to-end DGMs. Posterior regularization (PR) offers a principled framework to impose structured constraints on probabilistic models, but has limited …
While deep learning has achieved remarkable results on various applications, it is usually data hungry and struggles to learn over non-stationary data stream. To solve these two limits, the deep learning model should not only be able to learn from a few of data, but also incrementally learn new concepts from data strea…
In this paper, we introduce an approach for leveraging available data across multiple locales sharing the same language to 1) improve domain classification model accuracy in Spoken Language Understanding and user experience even if new locales do not have sufficient data and 2) reduce the cost of scaling the domain cla…
Double Machine Learning estimators are asymptotically inadmissible under structure-agnostic models.
New theory controls compression change probability without prior knowledge.
New algorithm learns from sparse data without knowing sparsity index.
Due to insufficient training data and the high computational cost to train a deep neural network from scratch, transfer learning has been extensively used in many deep-neural-network-based applications. A commonly used transfer learning approach involves taking a part of a pre-trained model, adding a few layers at the …
When fitting Bayesian machine learning models on scarce data, the main challenge is to obtain suitable prior knowledge and encode it into the model. Recent advances in meta-learning offer powerful methods for extracting such prior knowledge from data acquired in related tasks. When it comes to meta-learning in Gaussian…
A dataset for evaluating engagement with scientific video lectures.
Explaining AI systems is fundamental both to the development of high performing models and to the trust placed in them by their users. The Shapley framework for explainability has strength in its general applicability combined with its precise, rigorous foundation: it provides a common, model-agnostic language for AI e…
While recent progress has spawned very powerful machine learning systems, those agents remain extremely specialized and fail to transfer the knowledge they gain to similar yet unseen tasks. In this paper, we study a simple reinforcement learning problem and focus on learning policies that encode the proper invariances …
In many real-world reinforcement learning applications, access to the environment is limited to a fixed dataset, instead of direct (online) interaction with the environment. When using this data for either evaluation or training of a new policy, accurate estimates of discounted stationary distribution ratios -- correct…
Code search and comprehension have become more difficult in recent years due to the rapid expansion of available source code. Current tools lack a way to label arbitrary code at scale while maintaining up-to-date representations of new programming languages, libraries, and functionalities. Comprehensive labeling of sou…
Generalized zero-shot learning (GZSL) tackles the problem of learning to classify instances involving both seen classes and unseen ones. The key issue is how to effectively transfer the model learned from seen classes to unseen classes. Existing works in GZSL usually assume that some prior information about unseen clas…
Method detects new physics signals without prior knowledge.
Proposes a framework for generating explainable AI exemplars.
First proper learning algorithm for Gaussian halfspaces with matching sample and computational complexity.
TiAda adapts adaptive gradient methods for nonconvex minimax optimization.
Paper proposes a method to estimate scientific parameters in hybrid models without relying on model architecture.
GACBO optimizes unknown causal graphs with interventions.
In this paper we study the setting where features are added or change interpretation over time, which has applications in multiple domains such as retail, manufacturing, finance. In particular, we propose an approach to provably determine the time instant from which the new/changed features start becoming relevant with…
New approach makes deep reinforcement learning robust without assuming adversary knowledge.
This work considers an estimation task in compressive sensing, where the goal is to estimate an unknown signal from compressive measurements that are corrupted by additive pre-measurement noise (interference, or clutter) as well as post-measurement noise, in the specific setting where some (perhaps limited) prior knowl…
Sharp-MAML improves MAML by reducing saddle points in few-shot learning.
We introduce GLR-klUCB, a novel algorithm for the piecewise iid non-stationary bandit problem with bounded rewards. This algorithm combines an efficient bandit algorithm, kl-UCB, with an efficient, parameter-free, changepoint detector, the Bernoulli Generalized Likelihood Ratio Test, for which we provide new theoretica…