Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches · HackerPapers discussions

Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches — mentioned by timkam

Sat, 10 Jul 2021 16:58:26 GMT

I think when looking at least at large scale applications in the context of games (and not just super-expensive showcases), like in the Stockfish chess engine, we see that it's not primarily about depth, it's about architecture design. Reference: start here https://stockfishchess.org/blog/2021/stockfish-14/ and go down the rabbit hole... In the broadly useful domain of recommender systems (which typically make use of some type of RL-like feedback loop, but can be implemented using simple clustering approaches), at least in 2019, neural network-based approaches didn't seem to fair too well…

Paper and discussion history. A mention is not an endorsement.

Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches — mentioned by tomkat0789

Tue, 30 Mar 2021 15:49:46 GMT

+1 to this from someone who learned the math behind ML in a PhD and was looking forward to being a gatekeeper :) My favorite academic paper ever [0] was a comparison against a bunch of dimensionality reduction algorithms and 100 year old PCA was tough to beat! Glad I was able to pivot my career out of AI and ML. My PhD wasn't at Stanford, MIT, et al so I couldn't find any jobs doing the "actual research" - if they existed at all outside academia. EDIT to add another funny "frustration" paper more directly related to ML [1]. I consider DR is more of a data analysis thing. [0]: van der Maaten…

Paper and discussion history. A mention is not an endorsement.

Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches — mentioned by mkasu

Wed, 19 Aug 2020 09:46:26 GMT

Yes, the seeming performance of (especially) neural models compared to traditional models is probably the main factor. Although, some voices[1] argue that traditional or much simpler approaches still often do a similar job compared to super over-engineered models, especially when going even slightly beyond an existing target-dataset or task. I'd argue, that improving the ML models is really the job of ML researchers and should be mainly targeting ML conferences like AAAI (Adv. of AI). In other conferences (directly targeting NLP, CV, Comp. Biology, etc.) it should be the main job to combine…

Paper and discussion history. A mention is not an endorsement.

Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches — mentioned by timkam

Sat, 28 Dec 2019 18:44:52 GMT

There are recent works that question whether "deep" learning algorithms, and in particular neural networks, are really advancing the state of the art of recommender systems: https://arxiv.org/pdf/1907.06902.pdf (Best Paper Award, RecSys 2019). It is strange that the blog post fails to mention this.

Paper and discussion history. A mention is not an endorsement.

Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches — HN submission

Wed, 07 Aug 2019 11:13:36 GMT

Are We Making Much Progress? Analysis of Recent Neural Recommendation Approaches

86 points; 17 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches — HN submission

Fri, 02 Aug 2019 08:36:45 GMT

A Worrying Analysis of Recent Neural Recommendation Approaches

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches — HN submission

Mon, 29 Jul 2019 13:50:33 GMT

A Worrying Analysis of Recent Neural Recommendation Approaches

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches — HN submission

Sun, 28 Jul 2019 13:34:30 GMT

A Worrying Analysis of Recent Neural Recommendation Approaches

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches — HN submission

Wed, 24 Jul 2019 01:21:09 GMT

Are We Making Much Progress? Analysis of Recent Neural Recommendation Approaches

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches — HN submission

Mon, 22 Jul 2019 02:49:52 GMT

A Worrying Analysis of Recent Neural Recommendation Approaches

245 points; 82 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches — HN submission

Thu, 18 Jul 2019 17:57:43 GMT

Are We Making Much Progress with Neural Networks?

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.