Fix type mismatch bug in NashMTL

[ValerianRey]

• Move cast of alpha to torch.Tensor out of the condition on the step value
• Add changelog entry

Notes:

• self.prvs_alpha is always a numpy array, so in both cases (if (self.step % self.update_weights_every) == 0: and else), we have to cast alpha to a Tensor.
• In the original implementation of https://github.com/AvivNavon/nash-mtl/blob/main/methods/weight_methods.py#L238, there was already a mismatch of type, with alpha being a tensor when entering the condition (if (self.step % self.update_weights_every) == 0), and being a numpy array otherwise, but the following line (weighted_loss = sum([losses[i] * alpha[i] for i in range(len(alpha))])) made it work regardless.

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Files with missing lines	Coverage Δ
src/torchjd/aggregation/nash_mtl.py	88.23% <100.00%> (ø)

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.