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.
AuxiLearn combines auxiliary tasks into a single loss function.
Improves deep learning models by blending gradients from training loss and auxiliary objective.
One approach to deal with the statistical inefficiency of neural networks is to rely on auxiliary losses that help to build useful representations. However, it is not always trivial to know if an auxiliary task will be helpful for the main task and when it could start hurting. We propose to use the cosine similarity be…
Improved motion prediction for self-driving cars using trajectory sets and auxiliary losses.
Learning with auxiliary tasks can improve the ability of a primary task to generalise. However, this comes at the cost of manually labelling auxiliary data. We propose a new method which automatically learns appropriate labels for an auxiliary task, such that any supervised learning task can be improved without requiri…
HydaLearn dynamically adjusts task weights for better MTL performance.
Despite recent advances in training recurrent neural networks (RNNs), capturing long-term dependencies in sequences remains a fundamental challenge. Most approaches use backpropagation through time (BPTT), which is difficult to scale to very long sequences. This paper proposes a simple method that improves the ability …
Recent work has noted that all bad local minima can be removed from neural network loss landscapes, by adding a single unit with a particular parameterization. We show that the core technique from these papers can be used to remove all bad local minima from any loss landscape, so long as the global minimum has a loss o…
Malware detection is a popular application of Machine Learning for Information Security (ML-Sec), in which an ML classifier is trained to predict whether a given file is malware or benignware. Parameters of this classifier are typically optimized such that outputs from the model over a set of input samples most closely…
We propose self-teaching networks to improve the generalization capacity of deep neural networks. The idea is to generate soft supervision labels using the output layer for training the lower layers of the network. During the network training, we seek an auxiliary loss that drives the lower layer to mimic the behavior …
Aux-NAS uses auxiliary labels to improve primary task performance without extra inference cost.
Study optimal consumption for loss-averse agents considering past spending peaks.
In this paper, we explore the ways to improve POS-tagging using various types of auxiliary losses and different word representations. As a baseline, we utilized a BiLSTM tagger, which is able to achieve state-of-the-art results on the sequence labelling tasks. We developed a new method for character-level word represen…
REGAIN learns optimal auxiliary directions for forecast reconciliation.
Decision making in automated driving is highly specific to the environment and thus semantic segmentation plays a key role in recognizing the objects in the environment around the car. Pixel level classification once considered a challenging task which is now becoming mature to be productized in a car. However, semanti…
This work addresses encoding biases in neural networks by tailoring models with unsupervised losses.
Conditional generative models enjoy remarkable progress over the past few years. One of the popular conditional models is Auxiliary Classifier GAN (AC-GAN), which generates highly discriminative images by extending the loss function of GAN with an auxiliary classifier. However, the diversity of the generated samples by…
Trans-Ising combines auxiliary datasets to estimate high-dimensional Ising models.
A method corrects bias in estimating a high-dimensional classification rule using auxiliary outcomes.
TILT improves target domain performance by penalizing an auxiliary component on unlabeled target inputs.
We propose gradient adversarial training, an auxiliary deep learning framework applicable to different machine learning problems. In gradient adversarial training, we leverage a prior belief that in many contexts, simultaneous gradient updates should be statistically indistinguishable from each other. We enforce this c…
Study improves interpretability in generative models by disentangling latent variables in scientific datasets.
VAV method optimizes learning rate for faster, stable SGD convergence.
Many popular first-order optimization methods (e.g., Momentum, AdaGrad, Adam) accelerate the convergence rate of deep learning models. However, these algorithms require auxiliary parameters, which cost additional memory proportional to the number of parameters in the model. The problem is becoming more severe as deep l…
DHEN improves CVR prediction for ads with multitask learning and auxiliary loss.
Intervention loss stabilizes GAN training and reduces mode collapse.
Accurately annotating large scale dataset is notoriously expensive both in time and in money. Although acquiring low-quality-annotated dataset can be much cheaper, it often badly damages the performance of trained models when using such dataset without particular treatment. Various methods have been proposed for learni…
Sampling a fraction of pairs can match full evaluation in machine learning losses.
In supervised binary hashing, one wants to learn a function that maps a high-dimensional feature vector to a vector of binary codes, for application to fast image retrieval. This typically results in a difficult optimization problem, nonconvex and nonsmooth, because of the discrete variables involved. Much work has sim…
Logsy detects anomalies in logs using a novel classification-based approach.
SXL embeds spatial autocorrelation into neural networks for better geographic data learning.
Zero-shot contrastive loss improves text-guided image style transfer without extra training.
Model predicts operational risk using HMMs with economic covariates.
This paper proposes a Convolutional Neural Network (CNN) inspired by Multitask Learning (MTL) and based on speech features trained under the joint supervision of softmax loss and center loss, a powerful metric learning strategy, for the recognition of emotion in speech. Speech features such as Spectrograms and Mel-freq…
Developing a differentially private deep learning algorithm is challenging, due to the difficulty in analyzing the sensitivity of objective functions that are typically used to train deep neural networks. Many existing methods resort to the stochastic gradient descent algorithm and apply a pre-defined sensitivity to th…
New method uses correlated auxiliary feedback to reduce regret in parameterized bandits.
In-N-Out improves model robustness to out-of-distribution data.
We present a technique to improve the transferability of deep representations learned on small labeled datasets by introducing self-supervised tasks as auxiliary loss functions. While recent approaches for self-supervised learning have shown the benefits of training on large unlabeled datasets, we find improvements in …
Improved GP models for fast training and good performance.
Researchers identify valid auxiliary functions for extreme value distributions and their max-domains of attraction.
We study the problem of learning representations with controllable connectivity properties. This is beneficial in situations when the imposed structure can be leveraged upstream. In particular, we control the connectivity of an autoencoder's latent space via a novel type of loss, operating on information from persisten…
Auxiliary Tuning adapts pre-trained models for novel tasks efficiently.
The paper improves high-dimensional linear regression prediction and estimation using auxiliary samples.
We consider the estimation of heterogeneous treatment effects with arbitrary machine learning methods in the presence of unobserved confounders with the aid of a valid instrument. Such settings arise in A/B tests with an intent-to-treat structure, where the experimenter randomizes over which user will receive a recomme…
Method reweights auxiliary tasks to reduce data need for main task.
This paper reviews dMTL and methods for selecting auxiliary tasks.
Statistical inference is considered for variables of interest, called primary variables, when auxiliary variables are observed along with the primary variables. We consider the setting of incomplete data analysis, where some primary variables are not observed. Utilizing a parametric model of joint distribution of prima…
MFAI uses gradient boosted trees to leverage auxiliary info for scalable Bayesian matrix factorization.