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.
Tricks adversarial attacks to target specific classes, improving classifier accuracy.
Method transfers knowledge without label overlap, source data, or target architecture consistency.
The task of learning a sentiment classification model that adapts well to any target domain, different from the source domain, is a challenging problem. Majority of the existing approaches focus on learning a common representation by leveraging both source and target data during training. In this paper, we introduce a …
Reweighting training data to better represent new tasks.
Trained recurrent networks are powerful tools for modeling dynamic neural computations. We present a target-based method for modifying the full connectivity matrix of a recurrent network to train it to perform tasks involving temporally complex input/output transformations. The method introduces a second network during…
Paper proposes a method to learn linear regression models using multiple pre-trained models.
Sourcerer uses deep learning to map land cover from limited labeled data.
DiffATD efficiently discovers targets in partially observable environments using diffusion dynamics.
In this paper, we propose a method for training neural networks when we have a large set of data with weak labels and a small amount of data with true labels. In our proposed model, we train two neural networks: a target network, the learner and a confidence network, the meta-learner. The target network is optimized to…
Framework improves policy generalizability under biased training data.
This paper ranks pre-trained DNNs using a novel SI measure.
In this paper, we propose "personal VAD", a system to detect the voice activity of a target speaker at the frame level. This system is useful for gating the inputs to a streaming on-device speech recognition system, such that it only triggers for the target user, which helps reduce the computational cost and battery co…
Domain randomization (DR) is a successful technique for learning robust policies for robot systems, when the dynamics of the target robot system are unknown. The success of policies trained with domain randomization however, is highly dependent on the correct selection of the randomization distribution. The majority of…
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 …
Proposes a method to generate diverse translations by conditioning on target domain.
CogMol designs novel drug-like molecules for SARS-CoV-2 targets.
We reveal a model rank that predicts successful recovery of target functions at overparameterization.
XMixup improves transfer learning accuracy by 1.9% with less training time.
The primary objective of domain adaptation methods is to transfer knowledge from a source domain to a target domain that has similar but different data distributions. Thus, in order to correctly classify the unlabeled target domain samples, the standard approach is to learn a common representation for both source and t…
Few-shot learning improves time-series forecasting with limited data.
Enhances neural network robustness with Mixup and TLAT.
In this work, we investigate a novel training procedure to learn a generative model as the transition operator of a Markov chain, such that, when applied repeatedly on an unstructured random noise sample, it will denoise it into a sample that matches the target distribution from the training set. The novel training pro…
GEFA predicts drug-target affinity using graph neural networks.
We observe that several existing policy gradient methods (such as vanilla policy gradient, PPO, A2C) may suffer from overly large gradients when the current policy is close to deterministic (even in some very simple environments), leading to an unstable training process. To address this issue, we propose a new method, …
Conformal Bayes under label shift: post-hoc calibration vs. in-training adaptation
This paper introduces a neural sampler for scalable sampling from complex distributions.
Distillation is an effective knowledge-transfer technique that uses predicted distributions of a powerful teacher model as soft targets to train a less-parameterized student model. A pre-trained high capacity teacher, however, is not always available. Recently proposed online variants use the aggregated intermediate pr…
Deep neural networks suffer from performance decay when there is domain shift between the labeled source domain and unlabeled target domain, which motivates the research on domain adaptation (DA). Conventional DA methods usually assume that the labeled data is sampled from a single source distribution. However, in prac…
TILT improves target domain performance by penalizing an auxiliary component on unlabeled target inputs.
We consider unsupervised domain adaptation: given labelled examples from a source domain and unlabelled examples from a related target domain, the goal is to infer the labels of target examples. Under the assumption that features from pre-trained deep neural networks are transferable across related domains, domain adap…
This paper evaluates targeted data poisoning attacks by focusing on the hardest samples, improving evaluation and defense strategies.
A new method selects training samples for fine-tuning using validation set inference.
Fine-tuning neural networks is widely used to transfer valuable knowledge from high-resource to low-resource domains. In a standard fine-tuning scheme, source and target problems are trained using the same architecture. Although capable of adapting to new domains, pre-trained units struggle with learning uncommon targe…
Unsupervised domain adaptation studies the problem of utilizing a relevant source domain with abundant labels to build predictive modeling for an unannotated target domain. Recent work observe that the popular adversarial approach of learning domain-invariant features is insufficient to achieve desirable target domain …
Auxiliary Tuning adapts pre-trained models for novel tasks efficiently.
A new method trains deep neural networks for open set domain adaptation without negative open set difference.
Sharp theory of neural network scaling laws for hierarchical targets.
Self-taught learning is a technique that uses a large number of unlabeled data as source samples to improve the task performance on target samples. Compared with other transfer learning techniques, self-taught learning can be applied to a broader set of scenarios due to the loose restrictions on the source data. Howeve…
Paper proposes a new loss function for conditional models using soft targets.
New method trains neural samplers to sample from multi-modal distributions efficiently.
The paper establishes limits of transfer learning with neural networks.
Transfer-learning and meta-learning are two effective methods to apply knowledge learned from large data sources to new tasks. In few-class, few-shot target task settings (i.e. when there are only a few classes and training examples available in the target task), meta-learning approaches that optimize for future task l…
Unsupervised models can provide supplementary soft constraints to help classify new target data under the assumption that similar objects in the target set are more likely to share the same class label. Such models can also help detect possible differences between training and target distributions, which is useful in a…
A drone catches another agile drone using competitive reinforcement learning.
Recent works have demonstrated that machine learning models are vulnerable to model inversion attacks, which lead to the exposure of sensitive information contained in their training dataset. While some model inversion attacks have been developed in the past in the black-box attack setting, in which the adversary does …
Recently, voice conversion (VC) without parallel data has been successfully adapted to multi-target scenario in which a single model is trained to convert the input voice to many different speakers. However, such model suffers from the limitation that it can only convert the voice to the speakers in the training data, …
We propose a simple algorithm to train stochastic neural networks to draw samples from given target distributions for probabilistic inference. Our method is based on iteratively adjusting the neural network parameters so that the output changes along a Stein variational gradient that maximumly decreases the KL divergen…
Study on neural networks' performance in sequential task learning.