ترغب بنشر مسار تعليمي؟ اضغط هنا

Improving Optimization for Models With Continuous Symmetry Breaking

85   0   0.0 ( 0 )
 نشر من قبل Robert Bamler
 تاريخ النشر 2018
والبحث باللغة English




اسأل ChatGPT حول البحث

Many loss functions in representation learning are invariant under a continuous symmetry transformation. For example, the loss function of word embeddings (Mikolov et al., 2013) remains unchanged if we simultaneously rotate all word and context embedding vectors. We show that representation learning models for time series possess an approximate continuous symmetry that leads to slow convergence of gradient descent. We propose a new optimization algorithm that speeds up convergence using ideas from gauge theory in physics. Our algorithm leads to orders of magnitude faster convergence and to more interpretable representations, as we show for dynamic extensions of matrix factorization and word embedding models. We further present an example application of our proposed algorithm that translates modern words into their historic equivalents.



قيم البحث

اقرأ أيضاً

Broad adoption of machine learning techniques has increased privacy concerns for models trained on sensitive data such as medical records. Existing techniques for training differentially private (DP) models give rigorous privacy guarantees, but apply ing these techniques to neural networks can severely degrade model performance. This performance reduction is an obstacle to deploying private models in the real world. In this work, we improve the performance of DP models by fine-tuning them through active learning on public data. We introduce two new techniques - DIVERSEPUBLIC and NEARPRIVATE - for doing this fine-tuning in a privacy-aware way. For the MNIST and SVHN datasets, these techniques improve state-of-the-art accuracy for DP models while retaining privacy guarantees.
We propose an extension to neural network language models to adapt their prediction to the recent history. Our model is a simplified version of memory augmented networks, which stores past hidden activations as memory and accesses them through a dot product with the current hidden activation. This mechanism is very efficient and scales to very large memory sizes. We also draw a link between the use of external memory in neural network and cache models used with count based language models. We demonstrate on several language model datasets that our approach performs significantly better than recent memory augmented networks.
We consider assortment optimization over a continuous spectrum of products represented by the unit interval, where the sellers problem consists of determining the optimal subset of products to offer to potential customers. To describe the relation be tween assortment and customer choice, we propose a probabilistic choice model that forms the continuous counterpart of the widely studied discrete multinomial logit model. We consider the sellers problem under incomplete information, propose a stochastic-approximation type of policy, and show that its regret -- its performance loss compared to the optimal policy -- is only logarithmic in the time horizon. We complement this result by showing a matching lower bound on the regret of any policy, implying that our policy is asymptotically optimal. We then show that adding a capacity constraint significantly changes the structure of the problem: we construct a policy and show that its regret after $T$ time periods is bounded above by a constant times $T^{2/3}$ (up to a logarithmic term); in addition, we show that the regret of any policy is bounded from below by a positive constant times $T^{2/3}$, so that also in the capacitated case we obtain asymptotic optimality. Numerical illustrations show that our policies outperform or are on par with alternatives.
We study reinforcement learning of chatbots with recurrent neural network architectures when the rewards are noisy and expensive to obtain. For instance, a chatbot used in automated customer service support can be scored by quality assurance agents, but this process can be expensive, time consuming and noisy. Previous reinforcement learning work for natural language processing uses on-policy updates and/or is designed for on-line learning settings. We demonstrate empirically that such strategies are not appropriate for this setting and develop an off-policy batch policy gradient method (BPG). We demonstrate the efficacy of our method via a series of synthetic experiments and an Amazon Mechanical Turk experiment on a restaurant recommendations dataset.
Denoising diffusion probabilistic models have been recently proposed to generate high-quality samples by estimating the gradient of the data density. The framework assumes the prior noise as a standard Gaussian distribution, whereas the corresponding data distribution may be more complicated than the standard Gaussian distribution, which potentially introduces inefficiency in denoising the prior noise into the data sample because of the discrepancy between the data and the prior. In this paper, we propose PriorGrad to improve the efficiency of the conditional diffusion model (for example, a vocoder using a mel-spectrogram as the condition) by applying an adaptive prior derived from the data statistics based on the conditional information. We formulate the training and sampling procedures of PriorGrad and demonstrate the advantages of an adaptive prior through a theoretical analysis. Focusing on the audio domain, we consider the recently proposed diffusion-based audio generative models based on both the spectral and time domains and show that PriorGrad achieves a faster convergence leading to data and parameter efficiency and improved quality, and thereby demonstrating the efficiency of a data-driven adaptive prior.

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا