Optimal task order improves continual learning performance.
problem Challenges in neural networks learning multiple tasks in sequence.
method Linear teacher-student model with latent factors, derived analytical expression.
result Two principles for optimal task order: least representative first and dissimilar adjacent tasks.
Sharing information between multiple tasks enables algorithms to achieve good generalization performance even from small amounts of training data. However, in a realistic scenario of multi-task learning not all tasks are equally related to each other, hence it could be advantageous to transfer information only between …
While recent continual learning methods largely alleviate the catastrophic problem on toy-sized datasets, some issues remain to be tackled to apply them to real-world problem domains. First, a continual learning model should effectively handle catastrophic forgetting and be efficient to train even with a large number o…
Existing deep multitask learning (MTL) approaches align layers shared between tasks in a parallel ordering. Such an organization significantly constricts the types of shared structure that can be learned. The necessity of parallel ordering for deep MTL is first tested by comparing it with permuted ordering of shared la…
Paper tackles high-order inference in structured prediction tasks.
problem Maximizing a score function on the space of labels in high-order Markov random fields.
method Generative model approach with two-stage convex optimization algorithm.
result Success in general high-order inference problems driven by hyperedge expansion properties.
Estimates multiple related causal graphs with shared causal order.
problem Discovering multiple related Gaussian DAGs with shared causal order.
method Proposes a l1/l2-regularized MLE for joint estimation of K linear structural equation models. result Joint estimator achieves better sample complexity and consistency in causal order recovery.
First-order ANIL learns shared representations even with overparametrization.
problem Lack of theoretical evidence for model-agnostic meta-learning (ANIL) learning shared representations.
method First-order ANIL with a linear two-layer network architecture, showing asymptotically low-rank solutions with overparametrization.
result First-order ANIL learns linear shared representations, even with overparametrization, and performs well in adaptation.
Improved rates for continual learning using SGD and last-iterate analysis.
problem Forgetting in overparameterized models after fitting multiple tasks.
method Developed novel SGD upper bounds for continual linear models and analyzed their performance.
result Established universal forgetting rates for continual learning.
Most of the existing approaches focus on specific visual tasks while ignoring the relations between them. Estimating task relation sheds light on the learning of high-order semantic concepts, e.g., transfer learning. How to reveal the underlying relations between different visual tasks remains largely unexplored. In th…
Meta-learning framework for few-shot one-class classification using order-equivariant networks.
problem Few labeled examples for positive class in one-class classification tasks.
method Order-equivariant networks for meta-learning a binary classifier conditioned on positive examples.
result Meta-learning framework outperforms baselines on unseen synthetic streams.
New optimization method improves generalization across various tasks.
problem Improving zeroth-order optimization for better generalization.
method Exponential tilting objective to connect zeroth-order optimization with sharpness-aware minimization.
result Achieves better generalization compared to vanilla zeroth-order baselines.
OP-GFNs sample candidates in order-preserving proportion to a learned reward function.
problem Sampling diverse candidates with varying rewards in multi-objective optimization.
method Order-Preserving GFlowNets (OP-GFNs) use a learned reward function consistent with a provided order on candidates.
result Training OP-GFNs sparsifies the reward landscape, focusing on higher-ranked candidates.
We present an attention-based ranking framework for learning to order sentences given a paragraph. Our framework is built on a bidirectional sentence encoder and a self-attention based transformer network to obtain an input order invariant representation of paragraphs. Moreover, it allows seamless training using a vari…
Sequences have become first class citizens in supervised learning thanks to the resurgence of recurrent neural networks. Many complex tasks that require mapping from or to a sequence of observations can now be formulated with the sequence-to-sequence (seq2seq) framework which employs the chain rule to efficiently repre…
Mini-Hes improves LFA model performance on HDI tasks with missing data.
problem Effective representation of high-dimensional, incomplete data for user behavior understanding.
method Proposes Mini-Hes, a parallelizable second-order LFA model using mini-block diagonal Hessian-free optimization.
result Mini-Hes outperforms state-of-the-art models in missing data estimation tasks on recommender system datasets.
The Neural Autoregressive Distribution Estimator (NADE) and its real-valued version RNADE are competitive density models of multidimensional data across a variety of domains. These models use a fixed, arbitrary ordering of the data dimensions. One can easily condition on variables at the beginning of the ordering, and …
New algorithm trains neural nets on simple skills to learn complex tasks faster.
problem Learning complex tasks through simple imitation.
method Train neural networks on simple, easy-to-learn skills to accelerate learning of complex, hard-to-learn tasks.
result Consistently outperforms state-of-the-art baseline in training speed and performance.
A new autoregressive model learns the order of graph generation tasks.
problem Generating graphs in a meaningful order when the canonical order is not obvious.
method Introduces a variant of autoregressive models that dynamically decides the autoregressive order based on data.
result Achieves state-of-the-art results on molecular graph generation benchmarks.
DMTG groups tasks for multi-task learning in one shot.
problem Efficiently grouping and training multiple tasks in machine learning.
method Formulates Multi-Task Grouping as a differentiable pruning problem, training all groups simultaneously.
result Significantly improves training efficiency and mitigates objective bias.
EPINE enhances network embedding by improving adjacency matrix-based high-order proximity.
problem Inaccurate and poorly designed calculation of high-order proximity in network embedding.
method EPINE redefines high-order proximity intuitively and proposes a scalable algorithm for accurate calculation.
result EPINE outperforms existing methods in network reconstruction, link prediction, and node classification.
A novel framework extracts essential factors from order flow data for high-frequency trading.
problem Challenges in extracting and utilizing order flow data due to its large volume and limitations of traditional techniques.
method Proposes a Context Encoder and Factor Extractor for unsupervised learning of important signals from order flow data.
result Extracts superior factors from order flow data, improving stock trend prediction and order execution tasks.
Self-supervised pretraining for heterogeneous hypergraphs improves graph-based tasks.
problem Capturing higher-order relations in heterogeneous hypergraphs.
method SPHH framework for self-supervised pretraining of heterogeneous HyperGNNs.
result SPHH consistently outperforms state-of-the-art baselines in various downstream tasks.
Paper proposes DigMA to generate controllable financial market orders.
problem Generating realistic financial market orders with controllability.
method DigMA model using conditional diffusion and meta agent.
result DigMA achieves superior controllability and generation fidelity.
One of the basic tasks for Bayesian networks (BNs) is that of learning a network structure from data. The BN-learning problem is NP-hard, so the standard solution is heuristic search. Many approaches have been proposed for this task, but only a very small number outperform the baseline of greedy hill-climbing with tabu…
Study develops advanced models to forecast complex LOB data.
problem Forecasting high-frequency data in a limit order book (LOB).
method Advanced multidimensional sequence-to-sequence models with compound multivariate embedding.
result Method outperforms other multivariate forecasting methods, achieving lowest forecasting error.
Learned optimizers trained on many tasks improve model training efficiency and generalization.
problem Training models efficiently and effectively with minimal user intervention.
method Developed a neural network-based hierarchical optimizer trained on thousands of tasks.
result The learned optimizers generalize better to unseen tasks and exhibit unique behaviors.
The paper improves ESG taxonomy and classifies sentences as sustainable or unsustainable.
problem Improving ESG taxonomy and classifying sentences based on ESG factors.
method For ESG taxonomy, used Sentence-BERT models. For sentence classification, combined RoBERTa with a multi-layer perceptron.
result Significant performance improvement and high accuracy in classifying sentences.
Proposes efficient sampling methods for solving linear inverse problems.
problem Solving linear inverse problems with computational efficiency and accuracy.
method Higher-order Langevin diffusion with pre-conditioning and annealing.
result Provable sampling from posterior distributions with accelerated convergence.
This paper bridges MTL and meta-learning, showing their shared structure and efficiency.
problem Improving generalization and adaptation in multi-task and few-shot learning.
method Theoretical analysis and empirical investigation of MTL and gradient-based meta-learning.
result MTL and GBML share similar optimization formulations and predictions over unseen tasks.
Efficient modelling of feature interactions underpins supervised learning for non-sequential tasks, characterized by a lack of inherent ordering of features (variables). The brute force approach of learning a parameter for each interaction of every order comes at an exponential computational and memory cost (Curse of D…
Study uses contrastive learning to analyze market order behavior.
problem Understanding diverse market order behaviors.
method Self-supervised learning with triplet loss for order representation.
result Identified distinct behavior types using K-means clustering.
Deep learning models compare performance on Limit Order Book tasks.
problem Comparing Deep Learning models for High Frequency Trading.
method Reviewed and compared state-of-the-art models on the same dataset.
result Multilayer Perceptrons perform comparably to CNN-LSTM architectures.
New model optimizes worker-task specialization for crowdsourcing.
problem Inferring correct labels from noisy answers across varying worker and task skills.
method Introduced a d-type specialization model to account for varying worker and task types, and proposed algorithms achieving optimal sample complexity. result Optimal label inference algorithms for crowdsourcing with unknown worker and task types.
Tackling binary program analysis problems has traditionally implied manually defining rules and heuristics, a tedious and time-consuming task for human analysts. In order to improve automation and scalability, we propose an alternative direction based on distributed representations of binary programs with applicability…
In this paper, we presented a novel convolutional neural network framework for graph modeling, with the introduction of two new modules specially designed for graph-structured data: the k-th order convolution operator and the adaptive filtering module. Importantly, our framework of High-order and Adaptive Graph Convo…
Method preserves order in hierarchical clustering of ordered data.
problem Order preserving hierarchical clustering of directed acyclic graphs.
method Combination of classical hierarchical clustering and ultrametric fitting.
result Optimal clustering preserves both cluster quality and order.
Autoregressive flow models can perform causal discovery and inference tasks.
problem Causal inference tasks such as causal discovery and interventional predictions.
method Using autoregressive flow models to estimate causal directions and make predictions.
result Autoregressive flows can accurately perform causal inference tasks without restrictive assumptions.
The quantification of diversification benefits due to risk aggregation plays a prominent role in the (regulatory) capital management of large firms within the financial industry. However, the complexity of today's risk landscape makes a quantifiable reduction of risk concentration a challenging task. In the present pap…
MPP trains a transformer to predict multiple physical systems, improving accuracy across various tasks.
problem Training models for specific physical systems is inefficient and requires fine-tuning.
method MPP trains a shared transformer on multiple heterogeneous physical systems, projecting fields into a shared embedding space.
result A single MPP-pretrained transformer outperforms task-specific models on all pretraining sub-tasks and downstream tasks.
We reduce the computational cost of Neural AutoML with transfer learning. AutoML relieves human effort by automating the design of ML algorithms. Neural AutoML has become popular for the design of deep learning architectures, however, this method has a high computation cost. To address this we propose Transfer Neural A…
Factorization machines (FMs) are a supervised learning approach that can use second-order feature combinations even when the data is very high-dimensional. Unfortunately, despite increasing interest in FMs, there exists to date no efficient training algorithm for higher-order FMs (HOFMs). In this paper, we present the …
A new method optimizes diffusion models for fine-tuning tasks efficiently.
problem Optimizing diffusion models for downstream tasks using nested bilevel structures.
method Formalizes the challenge as a generative bilevel optimization problem and introduces a first-order bilevel framework.
result Our method outperforms existing fine-tuning and hyperparameter search baselines.
JAWS audits predictive uncertainty under covariate shift using jackknife+ weighted methods.
problem Auditing predictive uncertainty under data distribution shifts.
method JAW and JAWA methods for distribution-free uncertainty quantification.
result JAW relaxes the jackknife+'s assumption of data exchangeability for covariate shift.
Direct numerical simulation of Stokes flow through an impermeable, rigid body matrix by finite elements requires meshes fine enough to resolve the pore-size scale and is thus a computationally expensive task. The cost is significantly amplified when randomness in the pore microstructure is present and therefore multipl…
Optimizes trade execution with reinforcement learning for limit orders.
problem Maximizing revenue in a limit order book with market and limit orders.
method Formulated as a dynamic allocation task, uses multivariate logistic-normal distributions for efficient training.
result Outperforms traditional strategies in simulated environments.
Second-order optimizers retain residual information after data deletion, affecting machine unlearning.
problem Residual information in second-order optimizers after data deletion.
method Comparison of first-order and second-order learners, eigendecomposition analysis.
result Second-order optimizers retain residual information, not detectable by first-order analysis.
HydaLearn dynamically adjusts task weights for better MTL performance.
problem Constant loss weights in MTL lead to poor results due to drifting relevance and varying mini-batch composition.
method HydaLearn uses mini-batch gradients to dynamically adjust task weights.
result HydaLearn improves performance on synthetic and real-world data.
Paper analyzes proper losses and their performance in machine learning tasks.
problem Understanding the performance of estimators and forecasters in machine learning tasks.
method Analyzes surrogate regret and convergence rates for strictly proper losses.
result Strongly proper losses achieve the optimal convergence rate.