Related papers: Never Train from Scratch: Fair Comparison of Long-…
Finetuning pretrained models occurs in a low-dimensional subspace of the full parameter space. Prior work has focused on characterizing this optimization subspace, but largely ignored the complementary question: why do certain directions…
In many real-world deployments of machine learning systems, data arrive piecemeal. These learning scenarios may be passive, where data arrive incrementally due to structural properties of the problem (e.g., daily financial data) or active,…
While deep learning is facing an homogenization across modalities led by Transformers, they are still challenged by shallow linear models in the time series forecasting task. Our hypothesis is that models should learn a direct link from…
Transfer learning is widely used to adapt large pretrained models to new tasks with only a small amount of new data. However, a challenge persists -- the features from the original task often do not fully cover what is needed for unseen…
Despite the remarkable practical success of transformer-based language models, recent work has raised concerns about their ability to perform state tracking. In particular, a growing body of literature has shown this limitation primarily…
A proper parametrization of state transition matrices of linear state-space models (SSMs) followed by standard nonlinearities enables them to efficiently learn representations from sequential data, establishing the state-of-the-art on a…
Deep neural networks are capable of modelling highly non-linear functions by capturing different levels of abstraction of data hierarchically. While training deep networks, first the system is initialized near a good optimum by greedy…
Recent years have seen significant advancements in foundation models through generative pre-training, yet algorithmic innovation in this space has largely stagnated around autoregressive models for discrete signals and diffusion models for…
Transformers underpin modern large language models (LLMs) and are commonly assumed to be behaviorally unstructured at random initialization, with all meaningful preferences emerging only through large-scale training. We challenge this…
In this paper, we study how the intrinsic nature of pre-training data contributes to the fine-tuned downstream performance. To this end, we pre-train different transformer-based masked language models on several corpora with certain…
Efficient exploration is a crucial challenge in deep reinforcement learning. Several methods, such as behavioral priors, are able to leverage offline data in order to efficiently accelerate reinforcement learning on complex tasks. However,…
Tokenization and transfer learning are two critical components in building state of the art time series foundation models for forecasting. In this work, we systematically study the effect of tokenizer design, specifically scaling and…
Supervised learning approaches to offline reinforcement learning, particularly those utilizing the Decision Transformer, have shown effectiveness in continuous environments and for sparse rewards. However, they often struggle with…
In recent years, numerous Transformer-based models have been applied to long-term time-series forecasting (LTSF) tasks. However, recent studies with linear models have questioned their effectiveness, demonstrating that simple linear layers…
Transfer learning allows us to train deep architectures requiring a large number of learned parameters, even if the amount of available data is limited, by leveraging existing models previously trained for another task. Here we explore the…
This research aims to leverage machine learning to improve stock price prediction and support informed investment decisions related to buying, selling, and holding assets. Specifically, this work investigates transformer-based models for…
Existing work on continual learning (CL) is primarily devoted to developing algorithms for models trained from scratch. Despite their encouraging performance on contrived benchmarks, these algorithms show dramatic performance drops in…
Ever since their conception, Transformers have taken over traditional sequence models in many tasks, such as NLP, image classification, and video/audio processing, for their fast training and superior performance. Much of the merit is…
We empirically demonstrate that a transformer pre-trained on country-scale unlabeled human mobility data learns embeddings capable, through fine-tuning, of developing a deep understanding of the target geography and its corresponding…
Sleep staging is a clinically important task for diagnosing various sleep disorders, but remains challenging to deploy at scale because it because it is both labor-intensive and time-consuming. Supervised deep learning-based approaches can…